Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15837
    Prev
    Next
    INDEX
    Explanations

    terms related to film festivals and cinematic discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     face
    -0.32
     crowds
    -0.31
     Obtenez
    -0.29
    capan
    -0.27
    Tudo
    -0.27
     salary
    -0.27
     personaje
    -0.27
     Face
    -0.26
     lay
    -0.26
     Mich
    -0.26
    POSITIVE LOGITS
    httphttps
    0.77
    Tembelea
    0.72
     utafitiHapana
    0.67
     Cinema
    0.66
    Cinema
    0.66
     препратки
    0.65
    UserScript
    0.63
     cinema
    0.63
     BoxFit
    0.61
    thâu
    0.60
    Activations Density 0.244%

    No Known Activations