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. 16421
    Prev
    Next
    INDEX
    Explanations

    indications of physical evidence related to crime scenes, especially bloodstains and fingerprints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    OGND
    -0.63
    انتهای
    -0.57
    ñores
    -0.54
    Spolja
    -0.53
    󠀠
    -0.52
     adapters
    -0.52
    нгред
    -0.52
    RegressionTest
    -0.51
    setViewportView
    -0.51
    ロウィン
    -0.49
    POSITIVE LOGITS
    principalTable
    0.36
    ərbaycan
    0.31
    ScopeManager
    0.29
    ngdoc
    0.28
    findpost
    0.28
     intptr
    0.28
     Obispo
    0.27
    Hentet
    0.27
    RTLD
    0.26
     finito
    0.26
    Activations Density 0.052%

    No Known Activations