© 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. 7-GEMMASCOPE-RES-16K
    11. 14259
    Prev
    Next
    INDEX
    Explanations

    terms related to the characterization of objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.40
    locationManager
    -0.35
     Mentioned
    -0.34
    fVar
    -0.33
    nativeElement
    -0.33
     operands
    -0.31
    렵
    -0.31
     Consideration
    -0.31
     препратки
    -0.30
    킵
    -0.30
    POSITIVE LOGITS
     characterize
    1.07
     characterizing
    1.06
     documenting
    1.04
     characterized
    1.03
    Characterization
    0.97
     characterizes
    0.96
     documented
    0.93
     characterised
    0.92
     caractéris
    0.92
    documented
    0.88
    Activations Density 0.748%

    No Known Activations