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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56709
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases and patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.75
    AndEndTag
    -0.72
    aarrggbb
    -0.71
     transfieras
    -0.60
    styleType
    -0.60
     '\\;'
    -0.60
     المعيارى
    -0.58
    testens
    -0.56
    InputBorder
    -0.55
    CodedInputStream
    -0.55
    POSITIVE LOGITS
    …~
    0.68
     Mahi
    0.68
    )…
    0.64
     Thine
    0.63
    ”…
    0.63
    !...
    0.62
     fossa
    0.62
    <!--[
    0.61
    )...
    0.60
    <h3>
    0.60
    Activations Density 0.002%

    No Known Activations