© 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. 14-GEMMASCOPE-RES-16K
    11. 8637
    Prev
    Next
    INDEX
    Explanations

    references to documentaries and their production details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unicórnio
    -0.48
     pozy
    -0.45
     økonom
    -0.43
     llavero
    -0.43
     AssemblyCulture
    -0.42
    AnimationsModule
    -0.42
     muñeco
    -0.41
     pelúcia
    -0.40
    automated
    -0.40
     fièvre
    -0.40
    POSITIVE LOGITS
     documentary
    0.72
     documentaries
    0.69
     journalism
    0.67
     reporter
    0.67
     journalist
    0.63
     investigative
    0.63
     journalistic
    0.60
    Documentary
    0.58
    reporter
    0.57
     оригіналу
    0.56
    Activations Density 0.179%

    No Known Activations