© 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. 55178
    Prev
    Next
    INDEX
    Explanations

    references to identification and documentation of plant specimens

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

    scientific specimens and documentation

    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
     moms
    -0.43
     mili
    -0.42
     kine
    -0.42
    ſelves
    -0.41
     granite
    -0.41
     Reſ
    -0.40
     civi
    -0.40
     Moms
    -0.39
     CommandType
    -0.39
    …
    -0.39
    POSITIVE LOGITS
     lenker
    0.55
    colgante
    0.52
    oredCriteria
    0.50
     fotográfico
    0.49
     ejemplares
    0.49
     billeder
    0.49
     illustrationer
    0.47
     eksemp
    0.46
     समीक्षाएं
    0.46
    twimg
    0.45
    Activations Density 0.055%

    No Known Activations