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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 15169
    Prev
    Next
    INDEX
    Explanations

    references to cookies and cookie-related policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hecht
    -0.77
    ListComponent
    -0.76
    HomeAsUpEnabled
    -0.71
    isContained
    -0.70
     استنادى
    -0.69
     vēl
    -0.69
    ArrowToggle
    -0.69
    tisti
    -0.68
    mybatisplus
    -0.67
     HasFactory
    -0.64
    POSITIVE LOGITS
     cookies
    2.23
     cookie
    2.19
     Cookies
    2.10
     Cookie
    2.05
    cookie
    1.89
    Cookie
    1.85
    Cookies
    1.85
    cookies
    1.81
     COOKIES
    1.75
     COOKIE
    1.74
    Activations Density 0.068%

    No Known Activations