© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8448
    Prev
    Next
    INDEX
    Explanations

    references to social roles and interactions within communities

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

    Follows "which", "it", "that", or "also"

    np_acts-logits-general · gemini-2.0-flash

    which is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Adds
    -1.04
    Removes
    -0.96
     Removes
    -0.95
     Sends
    -0.94
     Adds
    -0.94
    Goes
    -0.93
    Takes
    -0.92
    Gives
    -0.92
     Brings
    -0.91
     Theſe
    -0.91
    POSITIVE LOGITS
     also
    0.47
    brigens
    0.46
     end
    0.45
    resultCode
    0.45
     dis
    0.44
     lords
    0.44
     antaranya
    0.43
     directly
    0.43
    letzt
    0.43
     properly
    0.43
    Activations Density 1.026%

    No Known Activations