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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6811
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to stage and set design in theatrical productions

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

    Stage and set design

    np_acts-logits-general · gemini-2.0-flash

    stage design and production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.65
    httphttps
    -0.63
     للاسماء
    -0.55
    berdayakan
    -0.54
    mybatisplus
    -0.53
    SharedDtor
    -0.48
    TagMode
    -0.48
    новништво
    -0.47
     viewDidLoad
    -0.47
    Espèce
    -0.46
    POSITIVE LOGITS
     scen
    0.49
     scene
    0.48
     Scene
    0.44
     escen
    0.43
     stage
    0.43
    Життєпис
    0.41
    ніципа
    0.40
     Bühnen
    0.39
     onstage
    0.38
    Scen
    0.36
    Activations Density 0.132%

    No Known Activations