© 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. 8129
    Prev
    Next
    INDEX
    Explanations

    references to sample sizes and sampling in research studies

    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
     electricidad
    -0.65
     financeira
    -0.59
     segredo
    -0.57
     dirigir
    -0.54
    躇
    -0.54
     graças
    -0.53
     dirección
    -0.52
     finanzas
    -0.52
     inalámb
    -0.52
     Byr
    -0.52
    POSITIVE LOGITS
     sample
    1.53
     Sample
    1.52
    Sample
    1.45
    sample
    1.41
     SAMPLE
    1.38
    SAMPLE
    1.34
     Samples
    1.29
     samples
    1.27
    Samples
    1.20
     SAMPLES
    1.09
    Activations Density 0.092%

    No Known Activations