© 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. 54083
    Prev
    Next
    INDEX
    Explanations

    key elements and factors involved in biological processes and mechanisms

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

    common grammatical structures

    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
     tė
    -0.40
     šķ
    -0.39
    oredCriteria
    -0.39
    Unione
    -0.37
     idéia
    -0.35
     ajudá
    -0.35
     AssemblyTitle
    -0.34
     dė
    -0.34
    occuper
    -0.34
     loob
    -0.32
    POSITIVE LOGITS
    Биография
    0.59
     gynhyrchwyd
    0.55
     bio
    0.51
     scientist
    0.50
     Bio
    0.48
     makeStyles
    0.48
     Biosciences
    0.47
     labs
    0.47
     scientists
    0.46
     fides
    0.46
    Activations Density 1.243%

    No Known Activations