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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-GEMMASCOPE-RES-16K
    6. 8754
    Prev
    Next
    INDEX
    Explanations

    specific tokens or characters that relate to technical or programming concepts

    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
    الإنجليزية
    -0.67
    AsUp
    -0.67
     itſelf
    -0.64
     alternativo
    -0.64
    djangoproject
    -0.61
     themſelves
    -0.61
     Chriftian
    -0.60
    ReusableCell
    -0.60
     ſever
    -0.58
    bootstrapcdn
    -0.58
    POSITIVE LOGITS
     the
    0.95
    wixt
    0.85
     an
    0.71
     its
    0.69
     a
    0.68
    Concerning
    0.67
    parseFrom
    0.65
    namental
    0.65
     Concerning
    0.65
     بشأن
    0.64
    Activations Density 0.315%

    No Known Activations