© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1713
    Prev
    Next
    INDEX
    Explanations

    awards and nominations in the film industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pipette
    -0.57
     Cyto
    -0.45
     immuno
    -0.44
    crizione
    -0.43
     Samaria
    -0.43
    zzini
    -0.42
    localctx
    -0.42
     Infórmanos
    -0.42
    EndInit
    -0.42
    istiques
    -0.42
    POSITIVE LOGITS
     film
    2.28
     movie
    2.21
     films
    2.17
     Film
    2.09
     cinema
    2.08
     movies
    2.06
     Films
    1.99
    film
    1.98
     filmmakers
    1.98
     Movie
    1.97
    Activations Density 1.164%

    No Known Activations