© 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. 55529
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to optional values and their structures in programming

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

    Integer parsing

    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
    RTLR
    -0.67
    ThroughAttribute
    -0.59
    MLLoader
    -0.57
    UrlResolution
    -0.56
     mxArray
    -0.48
     HasFactory
    -0.48
     regeringen
    -0.47
    最快更新
    -0.47
    StoryboardSegue
    -0.47
    nants
    -0.47
    POSITIVE LOGITS
     numbers
    0.58
     parseInt
    0.53
     number
    0.52
    parseInt
    0.51
     Number
    0.51
     Integer
    0.50
    ToInt
    0.50
     numerus
    0.50
    Integer
    0.49
    number
    0.49
    Activations Density 0.057%

    No Known Activations