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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 956
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with personal reflections and critique

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

    specific mentions of dates or numerical identifiers related to people

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

    end of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Мексичка
    -0.79
    "):
    
    -0.79
    Personendaten
    -0.75
    GEBURTSDATUM
    -0.74
    principalColumn
    -0.73
    )++;
    -0.68
     useParams
    -0.68
    ]<<"
    -0.66
    indd
    -0.65
    .[/
    -0.63
    POSITIVE LOGITS
     —
    0.58
     --
    0.56
    --
    0.53
    ——
    0.49
    ंदीखरीदारी
    0.49
     User
    0.46
    —
    0.44
    ArrowToggle
    0.44
    veno
    0.43
    User
    0.43
    Activations Density 0.017%

    No Known Activations