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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1622
    Prev
    Next
    INDEX
    Explanations

    terms related to integrated circuits and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Integr" or "int" followed by code/math-related terms

    np_acts-logits-general · gemini-2.0-flash

    integrate or integral words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    **
    -0.36
    cha
    -0.32
     quick
    -0.31
     s
    -0.31
     **
    -0.31
    nin
    -0.31
    Sa
    -0.31
    ako
    -0.30
     Sa
    -0.30
    ens
    -0.30
    POSITIVE LOGITS
    Tikang
    0.73
     فريبيس
    0.73
     Integr
    0.69
     Integration
    0.69
     INTEGR
    0.69
    Integration
    0.69
     Integrations
    0.68
     integrates
    0.67
     Exacts
    0.67
     integrate
    0.66
    Activations Density 0.117%

    No Known Activations