© 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. 27-GEMMASCOPE-RES-16K
    11. 9404
    Prev
    Next
    INDEX
    Explanations

    terms related to stunt performances and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uParam
    -0.47
     ProtoMessage
    -0.47
     StringTokenizer
    -0.45
     Stirn
    -0.41
     Infórmanos
    -0.40
    shops
    -0.40
    Lähteet
    -0.39
    httphttps
    -0.39
     redacción
    -0.38
    raits
    -0.38
    POSITIVE LOGITS
     climbing
    1.03
     climb
    1.00
     climbed
    0.93
     climbs
    0.89
     jumping
    0.89
    climb
    0.88
     acrob
    0.86
     gravity
    0.85
     jump
    0.85
     Climbing
    0.83
    Activations Density 0.332%

    No Known Activations