© 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. 79866
    Prev
    Next
    INDEX
    Explanations

    conditional statements and indicators of potential scenarios

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

    notice shall be included

    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
     
    -0.43
     inuti
    -0.41
    MathML
    -0.36
     pareja
    -0.36
     Feier
    -0.35
     épouse
    -0.35
     alkot
    -0.35
     Seitz
    -0.35
     voisins
    -0.34
     beroep
    -0.34
    POSITIVE LOGITS
     виправивши
    0.80
     Infórmanos
    0.80
    RegressionTest
    0.77
    AccessorTable
    0.73
    oa̍t
    0.71
    NameInMap
    0.70
    tanleria
    0.69
     الرياضيه
    0.68
    IUrlHelper
    0.67
     snippetHide
    0.66
    Activations Density 0.521%

    No Known Activations