© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 85085
    Prev
    Next
    INDEX
    Explanations

    occurrences of the dollar sign followed by a variable name, indicating the use of variables in a programming or scripting context

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

    variables like $subject, $message, $email, $value, $str

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.78
     queſta
    -0.77
     يتيمه
    -0.77
    parsedMessage
    -0.77
    BagLayout
    -0.77
     faſt
    -0.74
     GenerationType
    -0.74
    InjectAttribute
    -0.72
    expandindo
    -0.68
    MessageOf
    -0.68
    POSITIVE LOGITS
     $
    0.42
     The
    0.41
     the
    0.40
    The
    0.39
     du
    0.37
     my
    0.35
     les
    0.35
     Sänger
    0.34
    Figure
    0.33
     x
    0.32
    Activations Density 0.001%

    No Known Activations