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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11647
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to session management and user authentication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tersenyum
    -0.39
    pushFollow
    -0.37
    GoogleApiClient
    -0.37
     Administrativna
    -0.36
     criança
    -0.35
     aimé
    -0.35
     amorosa
    -0.35
     Infór
    -0.35
     Numerade
    -0.35
     lenker
    -0.35
    POSITIVE LOGITS
     $_
    0.99
    ,$_
    0.96
    =$_
    0.89
    ($_
    0.85
    $_
    0.80
    .$_
    0.80
     POST
    0.78
    POST
    0.77
    ".$_
    0.75
    )$_
    0.70
    Activations Density 0.192%

    No Known Activations