© 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. 10-GEMMASCOPE-RES-16K
    11. 6400
    Prev
    Next
    INDEX
    Explanations

    phrases indicating limits or statistics related to time and numerical values

    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
    niejs
    -0.48
     financiera
    -0.47
     mierda
    -0.46
    Havolalar
    -0.45
    ngrx
    -0.44
    ohjel
    -0.44
     siyang
    -0.43
     volando
    -0.42
     pubblica
    -0.42
     ře
    -0.41
    POSITIVE LOGITS
     hasta
    0.68
     upto
    0.68
     maximum
    0.65
     fino
    0.64
     até
    0.63
    Hasta
    0.63
    hasta
    0.63
     until
    0.63
     Hasta
    0.62
     až
    0.62
    Activations Density 0.131%

    No Known Activations