© 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. 101055
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating frequency or emphasis

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

    introduces subsequent action

    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
     sû
    -0.34
    Anmerkungen
    -0.31
     verres
    -0.31
     OMITBAD
    -0.30
     siècles
    -0.29
     ferie
    -0.29
     tilla
    -0.29
     convient
    -0.29
     allgeme
    -0.29
    wohl
    -0.29
    POSITIVE LOGITS
     had
    0.71
     gave
    0.70
     have
    0.69
     grew
    0.65
     took
    0.64
     went
    0.61
    rungsseite
    0.61
     drew
    0.60
     bore
    0.60
    írus
    0.60
    Activations Density 0.087%

    No Known Activations