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. 20-GEMMASCOPE-RES-131K
    6. 58265
    Prev
    Next
    INDEX
    Explanations

    placeholders or frequently occurring characters in a technical or coded context

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

    numbers and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.58
     dAtA
    -0.53
     uLocal
    -0.51
     NSCoder
    -0.48
     Engineered
    -0.48
    Jîn
    -0.46
    הערות
    -0.45
    ፩
    -0.43
    opsida
    -0.42
    amssymb
    -0.41
    POSITIVE LOGITS
     nemlig
    0.44
    intenant
    0.41
    TintMode
    0.39
     nämlich
    0.37
     encontraban
    0.35
    BagLayout
    0.35
     bowiem
    0.35
     though
    0.35
    RTSC
    0.35
    Neither
    0.35
    Activations Density 0.065%

    No Known Activations