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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 4704
    Prev
    Next
    INDEX
    Explanations

    references to input/output operations and related services in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -0.88
     ***!
    -0.87
    featureID
    -0.86
    principalColumn
    -0.84
    InjectAttribute
    -0.83
     fédé
    -0.81
     cherchés
    -0.81
     $#
    -0.80
    SourceChecksum
    -0.80
     Monfieur
    -0.80
    POSITIVE LOGITS
    io
    1.56
     io
    1.53
     IO
    1.40
    IO
    1.33
    IOException
    1.25
     Io
    1.20
    Io
    1.11
     IOException
    1.05
     ioe
    1.04
     Cio
    0.94
    Activations Density 0.066%

    No Known Activations