© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 7613
    Prev
    Next
    INDEX
    Explanations

    events or actions resulting in scores or advantages in sports

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

    Preceding words of numbers

    np_acts-logits-general · gemini-2.0-flash

    sports scores and outcomes

    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
     Recons
    -0.55
     tenté
    -0.54
     espoir
    -0.54
     myſelf
    -0.53
    RunAsync
    -0.52
    Manbalar
    -0.51
     Inscrivez
    -0.51
    localtime
    -0.50
    Datuak
    -0.49
     försö
    -0.48
    POSITIVE LOGITS
     overkill
    0.77
     rout
    0.71
     margin
    0.60
     AssemblyTitle
    0.59
    }{*}{
    0.58
    margin
    0.58
    tainty
    0.58
     easy
    0.58
     victory
    0.57
     Margin
    0.57
    Activations Density 0.141%

    No Known Activations