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. 7227
    Prev
    Next
    INDEX
    Explanations

    LaTeX package declarations and related syntax

    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
    enumi
    -0.77
    RuleContext
    -0.62
    WithFormat
    -0.62
    enumii
    -0.62
     ويكيپيديا
    -0.58
    CodedInputStream
    -0.57
    RegressionTest
    -0.56
    homonymie
    -0.55
    tsin
    -0.53
    Numerology
    -0.53
    POSITIVE LOGITS
    
    3.86
     resourceCulture
    0.92
    sizeCache
    0.87
    antium
    0.83
    
    0.83
    Panamoan
    0.71
    ніципалі
    0.69
     CanadaChoose
    0.69
     Hohen
    0.63
    ReturnValue
    0.62
    Activations Density 0.011%

    No Known Activations