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
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2479
    Prev
    Next
    INDEX
    Explanations

    references to sources or origins of information or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     llevo
    -0.38
    ftagPool
    -0.33
    SourceChecksum
    -0.33
     civils
    -0.33
     controls
    -0.32
     acides
    -0.31
     FormGroup
    -0.31
    をかけ
    -0.31
    Controls
    -0.31
    assertArray
    -0.31
    POSITIVE LOGITS
     sources
    0.76
     from
    0.74
     sourced
    0.73
     source
    0.71
     sourcing
    0.71
    来源
    0.69
    source
    0.68
    来自于
    0.66
     provenant
    0.66
     derives
    0.65
    Activations Density 0.479%

    No Known Activations