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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 62268
    Prev
    Next
    INDEX
    Explanations

    mathematical and algorithmic expressions or constructs related to algorithmic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical terminology and syntax related to algorithms, computational procedures, and mathematical notations in academic or technical documentation.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.58
    argout
    -0.46
    лтемелер
    -0.45
    +#+
    -0.42
    quares
    -0.42
    urous
    -0.40
    gino
    -0.40
     blinked
    -0.40
    lious
    -0.39
     blinking
    -0.38
    POSITIVE LOGITS
    WithIOException
    0.45
    WebMethod
    0.40
    awtextra
    0.40
     performance
    0.39
    nologue
    0.38
    PyExc
    0.37
    ArrowToggle
    0.37
    Vaya
    0.36
     屋根
    0.35
     version
    0.35
    Activations Density 0.142%

    No Known Activations