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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53473
    Prev
    Next
    INDEX
    Explanations

    variable and property declarations in programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     betweenstory
    -0.54
     afgelopen
    -0.38
     jongen
    -0.37
    RegressionTest
    -0.36
     już
    -0.36
     przecież
    -0.35
     rechange
    -0.33
    ISupport
    -0.33
    TagMode
    -0.32
     getSub
    -0.32
    POSITIVE LOGITS
     ballerina
    0.66
    Parcelize
    0.65
    endphp
    0.63
    Hochspringen
    0.63
    wiliwch
    0.61
     Paladin
    0.60
     Dux
    0.60
     heiress
    0.60
    majánló
    0.59
     Lyra
    0.59
    Activations Density 0.001%

    No Known Activations