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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12382
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as functions, return statements, and control flow constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    bitField
    -0.47
    culata
    -0.42
     cần
    -0.41
     needed
    -0.41
     son
    -0.39
    〈
    -0.39
     pre
    -0.37
    専
    -0.37
    tep
    -0.37
     needs
    -0.36
    POSITIVE LOGITS
    Personensuche
    1.00
     jScrollPane
    0.97
     виправивши
    0.87
     الحره
    0.85
     ProtoMessage
    0.85
    IntoConstraints
    0.85
     Wiktionnaire
    0.78
     ujednoznacz
    0.76
     utafitiHapana
    0.74
    ]")]
    0.73
    Activations Density 0.079%

    No Known Activations