© 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. 35-GEMMASCOPE-RES-16K
    11. 5599
    Prev
    Next
    INDEX
    Explanations

    references to videos and visual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.40
     ModelExpression
    -0.32
     indisponible
    -0.30
    AnchorStyles
    -0.29
    NamedQueries
    -0.28
     comen
    -0.28
     InputDecoration
    -0.27
     estad
    -0.27
     ISTAT
    -0.25
    uestas
    -0.25
    POSITIVE LOGITS
     video
    3.44
     videos
    3.17
    video
    2.92
     Video
    2.91
    Video
    2.83
     vidéo
    2.80
     Videos
    2.75
     видео
    2.66
     vídeo
    2.63
    videos
    2.63
    Activations Density 0.565%

    No Known Activations