© 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. 115178
    Prev
    Next
    INDEX
    Explanations

    requests for help and expressions of urgency

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

    pleading and requests for help

    np_acts-logits-general · gemini-2.5-flash-lite

    urgent pleas or direct requests for help (including imperative demands like "help me" or "please save/return [it]").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     autorytatywna
    -0.85
     surla
    -0.80
    ]")]
    -0.73
     незавершена
    -0.69
    <unused14>
    -0.68
    <unused8>
    -0.68
    <unused16>
    -0.68
     snippetHide
    -0.68
    <unused41>
    -0.68
    [@BOS@]
    -0.68
    POSITIVE LOGITS
    !
    0.45
    control
    0.38
    😥
    0.37
     desesper
    0.35
    😞
    0.34
    😭
    0.33
     control
    0.33
    !!!
    0.33
    💔
    0.31
    😰
    0.31
    Activations Density 0.069%

    No Known Activations