© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22486
    Prev
    Next
    INDEX
    Explanations

    terms related to restrictions and limitations

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

    restricted use

    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
    DebuggerStep
    -0.39
     atriz
    -0.36
    ={({
    -0.35
     Bewußt
    -0.35
    HasAnnotation
    -0.35
     fallu
    -0.33
    周泽楷
    -0.33
     helicópter
    -0.33
    ientôt
    -0.32
     defesa
    -0.32
    POSITIVE LOGITS
    SharedDtor
    0.66
    setVerticalGroup
    0.59
     betweenstory
    0.58
    tagHelperRunner
    0.58
    httphttps
    0.57
     AssemblyCulture
    0.56
    EDEFAULT
    0.54
    mybatisplus
    0.53
     ComVisible
    0.52
    LookAnd
    0.50
    Activations Density 0.000%

    No Known Activations