© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4153
    Prev
    Next
    INDEX
    Explanations

    references to physical stunts or risky activities

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

    "climbing" or being "down"

    np_acts-logits-general · gemini-2.0-flash

    climbing and falling actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    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
    -0.46
     redacción
    -0.44
     dredged
    -0.42
     sepol
    -0.41
    delwed
    -0.40
     comigo
    -0.39
     senhora
    -0.39
     razonable
    -0.39
    httphttps
    -0.39
     conmigo
    -0.39
    POSITIVE LOGITS
     climbing
    1.07
     climb
    0.96
    climbing
    0.88
     acrob
    0.88
     climbed
    0.88
     Climbing
    0.87
    climb
    0.85
     climbs
    0.85
    Climbing
    0.82
     climber
    0.81
    Activations Density 0.245%

    No Known Activations