Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 82980
    Prev
    Next
    INDEX
    Explanations

    organized and systematic frameworks for teaching and interventions

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

    structured, controlled, purposeful actions

    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
     Económica
    -0.54
    rungsseite
    -0.45
     Moscú
    -0.44
     Democrá
    -0.43
     mercancías
    -0.41
     Economía
    -0.41
     müş
    -0.41
     idéia
    -0.41
     emperador
    -0.40
     generales
    -0.39
    POSITIVE LOGITS
     purposeful
    0.80
     autorytatywna
    0.76
     deliberate
    0.75
     intentional
    0.72
     methodical
    0.70
     purposefully
    0.68
     structured
    0.66
    Guided
    0.64
    有序
    0.64
     orderly
    0.63
    Activations Density 0.055%

    No Known Activations