© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15360
    Prev
    Next
    INDEX
    Explanations

    information related to software package metadata and dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.59
    expandindo
    -0.59
    unknownFields
    -0.52
    (!__
    -0.50
    oredCriteria
    -0.47
     localObject
    -0.47
    thenReturn
    -0.47
    WebServlet
    -0.47
    FieldNumber
    -0.45
    Mucha
    -0.45
    POSITIVE LOGITS
     dependency
    0.75
    dependency
    0.65
     Resolution
    0.63
    SourceChecksum
    0.63
     risol
    0.62
    resolution
    0.61
     dependencies
    0.61
    Dependency
    0.60
     dependence
    0.60
     resolution
    0.59
    Activations Density 0.337%

    No Known Activations