Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7489
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of confusion or misunderstanding in a scenario

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     However
    -0.35
     But
    -0.34
     Yet
    -0.30
     Siempre
    -0.30
     особо
    -0.29
     but
    -0.29
    AUTH
    -0.28
    ✭✭
    -0.28
     Always
    -0.27
     Budaya
    -0.27
    POSITIVE LOGITS
    MigrationBuilder
    0.83
    thâu
    0.76
     CreateTagHelper
    0.71
     ModelExpression
    0.65
    UnsafeEnabled
    0.65
    featureID
    0.65
     StatelessWidget
    0.65
     ProtoMessage
    0.64
     ternyata
    0.63
    AntiForgeryToken
    0.63
    Activations Density 0.334%

    No Known Activations