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. 24-GEMMASCOPE-RES-16K
    6. 12664
    Prev
    Next
    INDEX
    Explanations

    actions related to sports and athletic performance

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

    preceding a comma

    np_acts-logits-general · gemini-2.0-flash

    1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defStyle
    -0.63
     vPvB
    -0.58
     SDLK
    -0.56
     Belf
    -0.55
    bcryptjs
    -0.54
    #+#
    -0.54
     للاسماء
    -0.52
    สือ
    -0.51
    })->
    -0.51
    TRAINING
    -0.50
    POSITIVE LOGITS
     bo
    0.69
     bir
    0.65
     card
    0.61
     par
    0.59
     shooting
    0.58
     birdie
    0.58
     pars
    0.55
     nett
    0.55
     rounds
    0.55
     useAppContext
    0.54
    Activations Density 0.127%

    No Known Activations