© 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. 22-GEMMASCOPE-RES-16K
    11. 4652
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making and the outcomes of actions taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CanadaChoose
    -0.68
    rungsseite
    -0.66
     calendriers
    -0.63
    :✨
    -0.59
     disambiguazione
    -0.58
     EconPapers
    -0.57
    RectangleBorder
    -0.56
    ölkerung
    -0.54
    énario
    -0.54
    UrlResolution
    -0.54
    POSITIVE LOGITS
     jsPsych
    0.41
    wapV
    0.40
    dafx
    0.37
     setEmail
    0.36
     LoginComponent
    0.33
    argout
    0.33
     pageable
    0.32
     onPostExecute
    0.31
     autorytatywna
    0.30
    labelledby
    0.30
    Activations Density 0.565%

    No Known Activations