© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 8205
    Prev
    Next
    INDEX
    Explanations

    negative expressions or terms associated with adverse outcomes or conditions

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

    -phase, D-dimer, B-spline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desmotivaciones
    -0.76
     gethan
    -0.74
     pérd
    -0.74
     feroit
    -0.72
     auroit
    -0.68
     pouvoit
    -0.68
     Infór
    -0.67
     étoit
    -0.65
     increí
    -0.65
     bordada
    -0.64
    POSITIVE LOGITS
    -
    1.10
    $-
    0.71
    ‐
    0.69
    -\
    0.69
    -,
    0.68
    '-
    0.68
    ‑
    0.68
    }-
    0.67
     -
    0.66
    )-
    0.66
    Activations Density 0.052%

    No Known Activations