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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 4871
    Prev
    Next
    INDEX
    Explanations

    references to the body or bodily-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rêver
    -0.61
     OnEnable
    -0.57
     revenus
    -0.56
     caccia
    -0.53
     rendus
    -0.51
     mezzanine
    -0.51
     Orrell
    -0.48
     кӀ
    -0.47
    ähne
    -0.47
     tweezers
    -0.47
    POSITIVE LOGITS
     body
    4.93
     Body
    4.38
    body
    4.33
    Body
    4.18
     BODY
    4.03
     bodies
    3.80
    BODY
    3.43
     Bodies
    3.39
    bodies
    3.18
     bodys
    3.01
    Activations Density 0.069%

    No Known Activations