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. 2596
    Prev
    Next
    INDEX
    Explanations

    structured data types and properties related to data entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a colon in code-related texts

    np_acts-logits-general · gemini-2.0-flash

    key-value assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    beruf
    -0.51
    ๆ
    -0.51
    ++;
    
    -0.50
    <eos>
    -0.50
    +='
    -0.48
    ffman
    -0.46
    ?,?,
    -0.44
    taler
    -0.44
     barrera
    -0.44
    <0x8C>
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.82
    CppCodeGen
    0.80
    Hozzáférés
    0.73
     ་་
    0.73
    migrationBuilder
    0.69
    IntoConstraints
    0.67
    tonode
    0.67
    ^(@)
    0.67
    fromnode
    0.66
     незавершена
    0.66
    Activations Density 0.228%

    No Known Activations