Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15369
    Prev
    Next
    INDEX
    Explanations

    comma-separated values in a numerical or tabular data format.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    parts of a data structure or code related to graphical elements such as widths and titles.

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

    structured data formats found in computer science applications.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    Code, punctuation, and special characters

    np_acts-logits-general · gemini-2.0-flash

    lists of numbers, code, or legal text

    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
    '
    -0.64
    :
    -0.57
    (
    -0.56
    ’
    -0.56
    -
    -0.55
     się
    -0.52
    "
    -0.51
    ?
    -0.51
    .
    -0.49
    /
    -0.49
    POSITIVE LOGITS
     Roskov
    1.35
    +#+#
    1.11
     etc
    1.07
    aarrggbb
    0.97
     للاسماء
    0.94
     '\\;'
    0.92
    DockStyle
    0.90
    etc
    0.90
    MigrationBuilder
    0.89
    IntoConstraints
    0.88
    Activations Density 0.414%

    No Known Activations