© 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. 38-GEMMASCOPE-RES-16K
    11. 8897
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinion and emotional reflection in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “...
    -1.04
    ......”
    -0.97
    ...”
    -0.91
    ---
    -0.89
    ...).
    -0.86
     --
    -0.84
    ..."
    -0.83
    ...),
    -0.82
    ...
    -0.82
     ---
    -0.82
    POSITIVE LOGITS
     🙂
    0.94
    –
    0.91
     –>
    0.88
    Â
    0.82
    —–
    0.76
    ——–
    0.76
    ?…
    0.73
    😦
    0.71
    🙂
    0.71
    .–
    0.71
    Activations Density 0.337%

    No Known Activations