© 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. 31-GEMMASCOPE-RES-131K
    11. 12542
    Prev
    Next
    INDEX
    Explanations

    context and components related to graphical user interface (GUI) elements and their actions within programming code

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

    UI elements and code statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.64
    IsContent
    -0.61
     esternos
    -0.59
    addPreferredGap
    -0.59
     $_(
    -0.59
     ―――――
    -0.59
    DockStyle
    -0.58
     AssemblyTitle
    -0.58
    __':
    -0.58
     مرئيه
    -0.57
    POSITIVE LOGITS
    .
    0.69
    MessageTagHelper
    0.44
     suddenly
    0.39
     biais
    0.38
     will
    0.38
     shall
    0.36
     adentro
    0.35
     should
    0.35
    ?.
    0.34
     became
    0.33
    Activations Density 0.014%

    No Known Activations