© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1353
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and their packages related to document formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelAdmin
    -0.60
    .'</
    -0.56
    صحاب
    -0.53
    enetrable
    -0.52
    \"></
    -0.50
     pes
    -0.50
     }}"></
    -0.50
    asional
    -0.50
    oprot
    -0.49
    enterOuterAlt
    -0.49
    POSITIVE LOGITS
     BoxDecoration
    0.82
    ViewFeatures
    0.73
     pinulongan
    0.73
    djangoproject
    0.72
    UserScript
    0.70
    WindowConstants
    0.70
    setupUi
    0.68
    aarrggbb
    0.66
    StandardCharsets
    0.66
     -*-
    0.64
    Activations Density 0.023%

    No Known Activations