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. 23-GEMMASCOPE-RES-131K
    6. 23238
    Prev
    Next
    INDEX
    Explanations

    closing brackets in programming code

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iſchen
    -0.79
    iſche
    -0.74
     Weiſe
    -0.70
    iſen
    -0.70
    <unused8>
    -0.70
    <unused14>
    -0.70
    <unused41>
    -0.69
    [@BOS@]
    -0.69
    <unused23>
    -0.69
    <unused43>
    -0.69
    POSITIVE LOGITS
    httphttps
    0.33
    于
    0.28
    ↵
    0.27
     asemenea
    0.26
    yarnpkg
    0.26
     déclar
    0.25
     anledning
    0.25
    AccessorTable
    0.25
     More
    0.24
    unknownFields
    0.24
    Activations Density 0.110%

    No Known Activations