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. 1749
    Prev
    Next
    INDEX
    Explanations

    code snippets and markup tags

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

    Code-related terms or tags

    np_acts-logits-general · gemini-2.0-flash

    code, kinetic energy, HIV, llette patterns

    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
    UnknownFieldSet
    -0.57
    ---*/
    -0.52
    ]";
    -0.50
    closePath
    -0.49
    ">*</
    -0.48
    ГЛА
    -0.48
    /−
    -0.47
    quatre
    -0.47
     børn
    -0.47
    }")]
    -0.47
    POSITIVE LOGITS
     "..\..\
    0.79
     "..\..\..\
    0.72
    runApp
    0.71
    httphttps
    0.65
    <code>
    0.65
     StatelessWidget
    0.58
    VIAF
    0.56
    awtextra
    0.56
     GenerationType
    0.56
     pinulongan
    0.56
    Activations Density 0.044%

    No Known Activations