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. 7-GEMMASCOPE-RES-16K
    6. 14867
    Prev
    Next
    INDEX
    Explanations

    email addresses and domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.73
    躇
    -0.71
    antMatchers
    -0.71
    DockStyle
    -0.67
     cherchés
    -0.67
    )";
    
    -0.66
    Hauptartikel
    -0.66
     onCreateView
    -0.66
    ineno
    -0.64
    ``.
    -0.63
    POSITIVE LOGITS
     email
    1.17
     getEmail
    1.15
    email
    1.15
    Email
    1.14
     Email
    1.13
     Emails
    1.09
     emails
    1.09
     emailing
    1.07
     EMAIL
    1.06
    getEmail
    1.06
    Activations Density 0.182%

    No Known Activations