© 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. 121639
    Prev
    Next
    INDEX
    Explanations

    specific programming terms and function calls related to data structures and control flow in coding contexts

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

    C/Unix file control and headers

    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
     ProtoMessage
    -0.49
     CanadaChoose
    -0.45
    الإنجليزية
    -0.43
    addGroup
    -0.38
    NegativeButton
    -0.35
     Мексичка
    -0.34
     ThemeData
    -0.34
    ModelBuilder
    -0.33
    UseVisualStyle
    -0.32
     /\.(
    -0.31
    POSITIVE LOGITS
    currentTarget
    0.93
    ClientRect
    0.89
     newArray
    0.79
     QtCore
    0.74
    rmi
    0.68
     resourceCulture
    0.68
     MediatR
    0.67
     بيها
    0.67
     FormData
    0.66
     nakalista
    0.61
    Activations Density 0.001%

    No Known Activations