Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6090
    Prev
    Next
    INDEX
    Explanations

    intensifiers and degree modifiers that express strong emotion or commitment

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

    following intensifiers

    np_acts-logits-general · gemini-2.0-flash

    adverbs and adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cresc
    -0.58
    jíma
    -0.49
    mela
    -0.49
    wholesome
    -0.48
     comprises
    -0.48
    inguém
    -0.48
     contains
    -0.47
    IsNotNull
    -0.47
    nehå
    -0.46
     lies
    -0.46
    POSITIVE LOGITS
    UnsafeEnabled
    0.84
    uxxxx
    0.82
    EndProject
    0.82
    DockStyle
    0.81
     aware
    0.79
     AssemblyCulture
    0.78
     nahilalakip
    0.78
    mybatisplus
    0.78
     HasFactory
    0.77
    setVerticalGroup
    0.76
    Activations Density 0.249%

    No Known Activations