© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2511
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific terminology and proper nouns related to research and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fastjson
    -0.36
     dép
    -0.35
     adel
    -0.35
    tonsoft
    -0.33
    
    -0.32
    Tembelea
    -0.31
     στιγ
    -0.31
    bitField
    -0.30
    ResponseEntity
    -0.29
     πως
    -0.29
    POSITIVE LOGITS
    transQ
    0.56
    ########.
    0.53
    PreferredItem
    0.51
     wuß
    0.50
    lussen
    0.50
    AsUp
    0.49
    #}
    0.49
    endphp
    0.49
     laſſen
    0.49
     obrazov
    0.48
    Activations Density 1.760%

    No Known Activations