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. 14177
    Prev
    Next
    INDEX
    Explanations

    statistical performance metrics in sports contexts

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

    Follows "All-" and a conference name

    np_acts-logits-general · gemini-2.0-flash

    All-conference awards

    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
    tagHelperRunner
    -0.68
     vettoriale
    -0.57
     chng
    -0.54
    eleste
    -0.51
    occupe
    -0.51
     avancée
    -0.51
    ribune
    -0.50
    itemBuilder
    -0.49
    Discord
    -0.48
     Repo
    -0.48
    POSITIVE LOGITS
     conference
    1.31
     Conference
    1.15
     league
    1.09
    conference
    1.09
    Conference
    1.07
     CONFERENCE
    0.94
    league
    0.92
     conferences
    0.91
     Confer
    0.82
     конферен
    0.79
    Activations Density 0.149%

    No Known Activations