Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2738
    Prev
    Next
    INDEX
    Explanations

    terms related to twisting, winding, and spiral shapes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.45
     censiti
    -0.44
    })`
    -0.40
    })).
    -0.39
    Sain
    -0.38
    )}</
    -0.37
    }'
    -0.37
     aceto
    -0.36
     UIAlert
    -0.36
    bootstrapcdn
    -0.36
    POSITIVE LOGITS
     winding
    1.10
     Winding
    1.03
     windings
    1.00
     espiral
    0.97
     spiral
    0.97
    winding
    0.97
    spiral
    0.95
     twisting
    0.94
     Spiral
    0.93
     twist
    0.92
    Activations Density 0.369%

    No Known Activations