© 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. 28-GEMMASCOPE-RES-16K
    6. 4050
    Prev
    Next
    INDEX
    Explanations

    references to testimonies or statements from individuals

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

    Follows possessive pronouns or titles

    np_acts-logits-general · gemini-2.0-flash

    noble estates and social circles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     murales
    -0.63
    MLLoader
    -0.62
     labourer
    -0.60
     $_"
    -0.57
    actéristi
    -0.56
     plakat
    -0.54
     marins
    -0.54
     syndical
    -0.54
     amarillas
    -0.53
     colectivo
    -0.53
    POSITIVE LOGITS
     estate
    0.43
     Schloss
    0.43
     ballroom
    0.42
     aristocratic
    0.41
     court
    0.39
    didSet
    0.39
     garden
    0.38
     castle
    0.36
     von
    0.36
     manor
    0.36
    Activations Density 0.427%

    No Known Activations