© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 35286
    Prev
    Next
    INDEX
    Explanations

    terms related to knowledge, understanding, and evaluation in research contexts

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

    to our knowledge

    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
     nonUne
    -0.46
    !("{
    -0.36
     Desen
    -0.34
    TokenNameLPAREN
    -0.34
    }}^{(
    -0.34
    部は
    -0.33
     dessins
    -0.33
    TypedDataSet
    -0.33
    Gön
    -0.33
    ชาย
    -0.31
    POSITIVE LOGITS
     SafeMath
    0.57
     ComVisible
    0.56
    featureID
    0.52
    enderror
    0.52
     onPostExecute
    0.52
    omock
    0.51
    oredCriteria
    0.51
     Roskov
    0.51
    StructEnd
    0.51
     kasarigan
    0.50
    Activations Density 0.047%

    No Known Activations