© 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. 25-GEMMASCOPE-RES-16K
    11. 15449
    Prev
    Next
    INDEX
    Explanations

    symbols and markup that resemble code or data formatting language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mtable
    -0.50
    gestone
    -0.46
    ftant
    -0.45
    ाहरण
    -0.45
    Демографія
    -0.43
    BeginContext
    -0.42
    hists
    -0.42
    躇
    -0.41
    idlertid
    -0.41
    oost
    -0.41
    POSITIVE LOGITS
    (/\
    0.57
    ..\..\
    0.54
     \
    0.53
    .\
    0.52
     "\
    0.52
    ("\\
    0.51
     EconPapers
    0.51
    :\
    0.50
     />\
    0.49
    "\
    0.48
    Activations Density 1.038%

    No Known Activations