Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 21424
    Prev
    Next
    INDEX
    Explanations

    concepts related to object-oriented programming and data structures

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

    sequences around structure

    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
     AspNetCore
    -0.53
     jadx
    -0.52
    EndGlobalSection
    -0.51
     ujednoznacz
    -0.50
     AttributeSet
    -0.48
    下载附件
    -0.47
    MemoryWarning
    -0.47
     surla
    -0.46
     pinulongan
    -0.46
    WebVitals
    -0.45
    POSITIVE LOGITS
     Herrn
    0.54
     Mr
    0.53
    Mr
    0.47
    enumi
    0.46
    ModelSerializer
    0.41
    isamment
    0.40
    impresa
    0.39
     menem
    0.38
     him
    0.36
    Ранее
    0.36
    Activations Density 0.840%

    No Known Activations