© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4226
    Prev
    Next
    INDEX
    Explanations

    references to customer service and personal commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    language about meeting customer needs and providing quality service/experiences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102

    promotional or customer-focused language emphasizing positive experiences, personalized service, and satisfaction.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    customer-oriented marketing language expressing commitment to support, quality service, and delivering a positive experience that meets your needs.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.53
    idlertid
    -0.41
    WindowConstants
    -0.41
    tyl
    -0.39
     lick
    -0.38
     Schengen
    -0.38
     peep
    -0.38
    laps
    -0.38
    findpost
    -0.38
     licks
    -0.37
    POSITIVE LOGITS
    AsUp
    0.51
    évaluateur
    0.49
    AutoField
    0.49
    tagHelperRunner
    0.46
    LookAnd
    0.44
    Portály
    0.43
    PreferredItem
    0.43
    Portail
    0.41
    attuale
    0.40
    Portale
    0.40
    Activations Density 0.571%

    No Known Activations