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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2138
    Prev
    Next
    INDEX
    Explanations

    HTML and formatting tags within the document

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

    closing tags and formatting elements in markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IGraphics
    -0.56
     Normdatei
    -0.54
    ";}
    -0.52
    .)}
    -0.52
    omeness
    -0.51
    ruptedException
    -0.51
    .\\
    -0.49
    fulness
    -0.48
     VIAF
    -0.48
    /}{
    -0.48
    POSITIVE LOGITS
    s
    0.93
    ‘
    0.87
    <em>
    0.83
    <strong>
    0.77
    <u>
    0.76
    says
    0.68
    sizeCache
    0.64
    still
    0.64
    solutions
    0.63
    <i>
    0.63
    Activations Density 0.257%

    No Known Activations