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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9570
    Prev
    Next
    INDEX
    Explanations

    references to source code and source control concepts

    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
    AlterField
    -0.60
     numberOfRows
    -0.55
     Audiodateien
    -0.52
    想想
    -0.49
    ricane
    -0.48
     вперед
    -0.47
    ştir
    -0.47
    <h2>
    -0.46
    ButterKnife
    -0.46
    XmlAccessorType
    -0.45
    POSITIVE LOGITS
     sources
    1.22
     Sources
    1.15
     SOURCE
    1.11
    Sources
    1.08
    sources
    1.06
     source
    1.04
    Fuentes
    0.96
     源
    0.96
    源
    0.96
     Source
    0.92
    Activations Density 0.144%

    No Known Activations