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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15659
    Prev
    Next
    INDEX
    Explanations

    references to literals, particularly string literals and their characteristics in code

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

    code literals

    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
    findpost
    -0.59
     onResponse
    -0.57
     Covid
    -0.54
    Byz
    -0.53
    ButtonModule
    -0.53
    postIndex
    -0.52
     Teams
    -0.52
    Covid
    -0.52
     Cow
    -0.51
    Schedulers
    -0.50
    POSITIVE LOGITS
    Literal
    2.16
    literal
    1.93
     Literal
    1.87
     literal
    1.80
     literals
    1.37
    Literals
    1.22
    LITERAL
    1.20
     Liter
    0.96
    literals
    0.95
    Liter
    0.91
    Activations Density 0.003%

    No Known Activations