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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 56121
    Prev
    Next
    INDEX
    Explanations

    references to different generations and the passage of tradition or values

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

    generations and inheritance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.59
     Ambiental
    -0.45
     hitam
    -0.44
     diarios
    -0.42
     ambientale
    -0.40
     fact
    -0.40
     telefónica
    -0.38
     úteis
    -0.37
     cuenca
    -0.37
     cardiaque
    -0.37
    POSITIVE LOGITS
     generations
    1.15
     Generation
    1.15
     generation
    1.13
    generation
    1.12
     Generations
    1.08
    Generation
    1.03
    generational
    1.02
     GENERATION
    1.02
    eneration
    0.95
    VersionUID
    0.88
    Activations Density 0.011%

    No Known Activations