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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8777
    Prev
    Next
    INDEX
    Explanations

    instances of the type 'int' in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     speech
    -0.63
     Speech
    -0.59
     SPEECH
    -0.56
    Speech
    -0.50
    speech
    -0.48
     derived
    -0.46
     branch
    -0.46
    vellous
    -0.41
    branch
    -0.41
    arsch
    -0.40
    POSITIVE LOGITS
     int
    0.94
    NameInMap
    0.64
    aarrggbb
    0.60
    MigrationBuilder
    0.56
    pushFollow
    0.54
    TagMode
    0.52
     RemoteException
    0.51
    parsedMessage
    0.50
     ints
    0.50
     ProtoMessage
    0.49
    Activations Density 0.043%

    No Known Activations