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. 9-GEMMASCOPE-RES-131K
    6. 6912
    Prev
    Next
    INDEX
    Explanations

    references to complete articles or stories

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

    full story, full review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.47
    tonsoft
    -0.47
     secas
    -0.45
     ſta
    -0.45
     faſt
    -0.44
     enfans
    -0.43
     vägen
    -0.42
     becauſe
    -0.42
     prêtres
    -0.42
     cúp
    -0.41
    POSITIVE LOGITS
     full
    0.96
     Full
    0.95
    Full
    0.85
     FULL
    0.75
    full
    0.75
    <bos>
    0.65
    FULL
    0.62
    RegressionTest
    0.54
     penuh
    0.54
     peł
    0.54
    Activations Density 0.006%

    No Known Activations