© 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. 13-GEMMASCOPE-RES-16K
    11. 8622
    Prev
    Next
    INDEX
    Explanations

    terms indicating usefulness or helpfulness in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیکھیے
    -0.60
    WebVitals
    -0.45
     kyse
    -0.43
    sidemargin
    -0.43
    makeText
    -0.42
    ńczy
    -0.42
    RTSC
    -0.39
     tanggung
    -0.39
    gonic
    -0.39
     aesthetics
    -0.37
    POSITIVE LOGITS
     helpful
    1.15
     useful
    1.13
    Useful
    1.09
     Useful
    1.06
    helpful
    1.01
     Helpful
    1.00
    useful
    0.99
    Helpful
    0.96
     útiles
    0.91
     ayuda
    0.85
    Activations Density 0.292%

    No Known Activations