© 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
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 958
    Prev
    Next
    INDEX
    Explanations

    references to ongoing effects, mentions of loss, and continuity in experiences or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.55
    encodeWith
    -0.49
     MainAxisSize
    -0.47
    uxxxx
    -0.47
     invokingState
    -0.47
    TagMode
    -0.46
     мәкал
    -0.46
     sice
    -0.45
    webElementXpaths
    -0.45
    isContained
    -0.44
    POSITIVE LOGITS
     rest
    3.69
     remainder
    2.70
    rest
    2.67
    Rest
    2.61
     Rest
    2.56
     resten
    2.52
     reste
    2.11
     remaining
    2.05
    remainder
    1.96
     resta
    1.92
    Activations Density 0.751%

    No Known Activations