© 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. 36-GEMMASCOPE-RES-16K
    11. 16186
    Prev
    Next
    INDEX
    Explanations

    references to the word "roll" and its variations, often in contexts related to movement or function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.61
    +#+#
    -0.58
    GIVEREF
    -0.55
     MenuView
    -0.54
    __':
    -0.53
     FetchType
    -0.50
    Personendaten
    -0.50
    esez
    -0.50
     kasarigan
    -0.50
     חיצוניים
    -0.50
    POSITIVE LOGITS
     roll
    3.03
     Roll
    2.81
     rolling
    2.69
     rolled
    2.67
    Roll
    2.66
     ROLL
    2.58
     rolls
    2.56
    roll
    2.56
    ROLL
    2.34
     Rolling
    2.25
    Activations Density 0.279%

    No Known Activations