© 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. 72561
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure

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

    code, math, spy, languages

    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
    UnusedPrivate
    -0.67
    TagMode
    -0.63
    Datuak
    -0.57
     Administrativna
    -0.55
    WriteTagHelper
    -0.54
    verifyException
    -0.53
    CppMethod
    -0.53
    ьаж
    -0.52
    RenderAtEndOf
    -0.52
    Referencies
    -0.51
    POSITIVE LOGITS
     själva
    0.38
    रीद
    0.32
     cop
    0.31
     desaparición
    0.31
    ワイイ
    0.31
     соответственно
    0.30
     diras
    0.29
     respectivamente
    0.29
     quello
    0.28
     supuesto
    0.28
    Activations Density 0.153%

    No Known Activations