© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13016
    Prev
    Next
    INDEX
    Explanations

    Java programming syntax related to file operations and request handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outputStream
    -0.54
     beziehungs
    -0.49
     Bergmann
    -0.47
    endsection
    -0.46
    __(/*!
    -0.45
    sendLogPayload
    -0.45
     currentValue
    -0.45
     Norden
    -0.44
    essentiel
    -0.44
     Felsen
    -0.44
    POSITIVE LOGITS
     freq
    0.96
     assoc
    0.93
     coeff
    0.93
     req
    0.90
     orig
    0.85
     Atty
    0.84
     Assoc
    0.84
     Freq
    0.84
     yrs
    0.82
     eqn
    0.82
    Activations Density 1.516%

    No Known Activations