© 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. 24-GEMMASCOPE-RES-16K
    11. 11298
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax related to function definitions and testing

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

    Mathematical operations and comparisons

    np_acts-logits-general · gemini-2.0-flash

    calculation or specification following of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.71
     indígen
    -0.55
    RTEE
    -0.54
     queſta
    -0.50
    ंदीखरीदारी
    -0.50
     Мексичка
    -0.49
    uxxxx
    -0.48
     CanadaChoose
    -0.48
    EndGlobal
    -0.48
    ſchaft
    -0.48
    POSITIVE LOGITS
     even
    0.57
     more
    0.43
     any
    0.41
     avulla
    0.41
     Varianten
    0.41
     different
    0.41
     larger
    0.40
    ậm
    0.40
     mis
    0.39
     cases
    0.39
    Activations Density 0.871%

    No Known Activations