© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13933
    Prev
    Next
    INDEX
    Explanations

    descriptions of personality traits and characteristics

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

    positive descriptions of people's character traits, particularly in the phrase "a [adjective] guy" or when describing someone as kind, generous, or having admirable qualities.

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

    positive, conversational descriptions of a person’s character or demeanor, especially praising someone as a nice, down-to-earth person

    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
     en
    -0.35
    хьтан
    -0.32
    گران
    -0.31
    StoreMessageInfo
    -0.29
     guess
    -0.29
    pushButton
    -0.29
    吐
    -0.29
     unfortunately
    -0.28
    Здравствуйте
    -0.28
     judgement
    -0.27
    POSITIVE LOGITS
    migrationBuilder
    0.69
    ftagPool
    0.63
     resourceCulture
    0.60
    sidemargin
    0.57
     صوتيه
    0.56
     الحره
    0.55
    featureID
    0.55
     AssemblyCompany
    0.54
     فريبيس
    0.54
    PMailer
    0.54
    Activations Density 0.381%

    No Known Activations