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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 88821
    Prev
    Next
    INDEX
    Explanations

    important concepts and terminology related to insights, goals, and classifications in various contexts

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

    highlighting importance

    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
     ervan
    -0.51
    addContainerGap
    -0.50
    ulity
    -0.50
     allemaal
    -0.48
     makeStyles
    -0.48
     sexes
    -0.47
    excess
    -0.47
     jagung
    -0.46
    (;;)
    -0.46
     migraines
    -0.46
    POSITIVE LOGITS
     important
    1.45
     Important
    1.38
    Important
    1.36
     importante
    1.34
    important
    1.33
     importantes
    1.19
    importante
    1.15
     importants
    1.12
     belangrijke
    1.09
     IMPORTANT
    1.08
    Activations Density 0.081%

    No Known Activations