© 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. 40-GEMMASCOPE-RES-16K
    11. 5324
    Prev
    Next
    INDEX
    Explanations

    phrases indicating questioning or inquiry about people, particularly focusing on their characteristics or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    postsleuth
    -0.46
     ExecuteAsync
    -0.42
     AspNetCore
    -0.41
    DockStyle
    -0.40
    postmedia
    -0.40
     Vikipedi
    -0.38
    tangentMode
    -0.35
    __["
    -0.34
    endcsname
    -0.34
    </thead>
    -0.33
    POSITIVE LOGITS
     considered
    1.59
     consider
    1.54
     considers
    1.48
     classify
    1.42
     regarded
    1.42
     termed
    1.38
     classified
    1.38
     regard
    1.35
     labeled
    1.35
     labelled
    1.34
    Activations Density 0.878%

    No Known Activations