© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 55128
    Prev
    Next
    INDEX
    Explanations

    tokens indicating operations or parameters related to networking and data processing

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

    C/C++ bitwise operations

    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
    ValueStyle
    -0.60
    awtextra
    -0.46
    Itoa
    -0.42
    Obrázky
    -0.41
    tagHelperRunner
    -0.41
     Statue
    -0.40
    сылкі
    -0.39
    Воз
    -0.39
    tagext
    -0.38
    FCC
    -0.38
    POSITIVE LOGITS
     >>=
    0.54
    errHandler
    0.51
    ENDIAN
    0.50
     Rumuni
    0.47
     reverse
    0.47
    iomanip
    0.47
    engaruhi
    0.46
     <<=
    0.46
     tulang
    0.46
    berdayakan
    0.45
    Activations Density 0.020%

    No Known Activations