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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11741
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to configuration and component systems in software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iented
    -0.40
     """",
    -0.37
    Stencil
    -0.35
     liev
    -0.34
     Meksiku
    -0.34
    anceled
    -0.33
     Leinster
    -0.33
     polystyrene
    -0.31
    apatalk
    -0.31
    avit
    -0.31
    POSITIVE LOGITS
     Spotify
    1.24
     playlist
    1.13
     playlists
    1.13
    Spotify
    1.09
     spotify
    1.07
    spotify
    0.95
     album
    0.93
     song
    0.90
     Playlist
    0.88
     songs
    0.88
    Activations Density 0.190%

    No Known Activations