© 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. 31-GEMMASCOPE-RES-16K
    11. 9496
    Prev
    Next
    INDEX
    Explanations

    words related to adaptations of stories into different formats, such as films or plays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to adaptations of books into other media formats like films, television shows, and plays.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rückkehr
    -0.34
     répar
    -0.33
    żesz
    -0.33
     dotyczą
    -0.32
     Mischung
    -0.32
     dotyczące
    -0.31
     mantenimiento
    -0.31
     lendemain
    -0.31
     garansi
    -0.31
     vermeiden
    -0.31
    POSITIVE LOGITS
     movie
    1.52
     film
    1.47
     movies
    1.35
     films
    1.33
     television
    1.32
    movie
    1.26
     TV
    1.24
    film
    1.23
     Movie
    1.19
     cinema
    1.19
    Activations Density 0.344%

    No Known Activations