© 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. 97490
    Prev
    Next
    INDEX
    Explanations

    string concatenation operations and syntax in code

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

    string concatenation and formatting

    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
    äule
    -0.38
     Autorisations
    -0.37
     Autorizaciones
    -0.37
     nonUne
    -0.36
     Chart
    -0.35
    ighorn
    -0.35
    chart
    -0.35
    [$
    -0.34
     chart
    -0.33
    overe
    -0.33
    POSITIVE LOGITS
    EndContext
    0.58
    bootstrapcdn
    0.57
    SequentialGroup
    0.52
    اریخ
    0.50
     Chwiliwch
    0.50
    DebuggerStep
    0.50
    下载附件
    0.48
    fortawesome
    0.48
     '\\;'
    0.47
     sumpay
    0.47
    Activations Density 0.162%

    No Known Activations