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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3205
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "body" in various contexts

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

    "body" or plural "bodies"

    np_acts-logits-general · gemini-2.0-flash

    body mass, body language, body of work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caw
    -1.01
    AddTagHelper
    -0.87
     Мексичка
    -0.85
     Squal
    -0.83
     Quail
    -0.83
     Kac
    -0.78
     acorns
    -0.77
     precip
    -0.77
     للمعارف
    -0.77
    |}{$
    -0.76
    POSITIVE LOGITS
     Body
    1.42
     BODY
    1.36
     body
    1.34
    body
    1.28
     bodies
    1.17
    Body
    1.17
     Bodies
    1.15
    BODY
    1.09
     bodys
    1.05
     Bod
    1.01
    Activations Density 0.158%

    No Known Activations