© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 12714
    Prev
    Next
    INDEX
    Explanations

    expressions of praise and admiration

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

    expressing praise or admiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pushFollow
    -0.37
    enterOuterAlt
    -0.35
    bag
    -0.32
    hust
    -0.32
    NavController
    -0.29
     quadr
    -0.29
    thag
    -0.29
     غم
    -0.29
    subs
    -0.29
     bag
    -0.28
    POSITIVE LOGITS
     praise
    2.45
     praises
    2.19
     praising
    2.16
     praised
    2.03
    praise
    1.98
     Praise
    1.98
    Praise
    1.80
     elog
    1.66
     compliments
    1.63
     compliment
    1.57
    Activations Density 0.169%

    No Known Activations