© 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. 99872
    Prev
    Next
    INDEX
    Explanations

    the presence of string delimiters such as quotes and triple quotes in the text

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

    code and math explanations

    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
     CanadaChoose
    -0.57
    TypedDataSet
    -0.54
    最快更新
    -0.52
     defaultstate
    -0.51
    #+#
    -0.51
     sebaliknya
    -0.51
     autorytatywna
    -0.49
     newState
    -0.49
     nahilalakip
    -0.49
    Ӕ
    -0.48
    POSITIVE LOGITS
    yntaxException
    0.38
    opsida
    0.36
    Firstly
    0.34
     Valerie
    0.32
     ho
    0.31
     According
    0.31
     Comédie
    0.31
    이는
    0.31
     Mej
    0.31
     Firstly
    0.31
    Activations Density 0.003%

    No Known Activations