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. 23534
    Prev
    Next
    INDEX
    Explanations

    interaction with a button or activation mechanism in a digital or mechanical context

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

    technical commands and processes

    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
    Cyfarwyddwr
    -0.48
     estekak
    -0.42
    CopyWith
    -0.40
     distribuir
    -0.39
     ancak
    -0.38
     Taktlose
    -0.38
     finalmente
    -0.38
    новништво
    -0.37
    richTextPanel
    -0.37
    KURZBESCHREIBUNG
    -0.37
    POSITIVE LOGITS
    fromnode
    0.45
    appé
    0.44
    :✨
    0.44
    hardy
    0.43
    ichord
    0.43
     poveznice
    0.42
     jsPsych
    0.41
    ArgumentParser
    0.41
     contour
    0.41
    WebControls
    0.41
    Activations Density 0.075%

    No Known Activations