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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 11508
    Prev
    Next
    INDEX
    Explanations

    terms related to negative health impacts or outcomes

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

    adverse outcomes and consequences

    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
     مشين
    -0.82
     ſche
    -0.76
    fjspx
    -0.75
    存于互联网档案馆
    -0.74
    EndInit
    -0.73
    ſelf
    -0.73
     Wikimedijinoj
    -0.72
    featureID
    -0.71
     ſch
    -0.71
    ReusableCell
    -0.71
    POSITIVE LOGITS
    Adverse
    0.49
     adverse
    0.49
     Adverse
    0.48
     almendras
    0.44
     deemed
    0.44
     sabido
    0.40
     pudieran
    0.39
     deberán
    0.39
    เหตุ
    0.39
    argli
    0.38
    Activations Density 0.016%

    No Known Activations