© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8461
    Prev
    Next
    INDEX
    Explanations

    statistical significance markers in research data

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

    P followed by less than

    np_acts-logits-general · gemini-2.0-flash

    p-value significance markers

    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
     work
    -1.40
     Work
    -1.26
    Work
    -1.24
    work
    -1.21
     WORK
    -1.06
    WORK
    -0.96
     Arbeit
    -0.85
    工作
    -0.81
     works
    -0.81
     trabalho
    -0.79
    POSITIVE LOGITS
    <
    0.55
     nhỏ
    0.54
    SMALL
    0.51
     SMALL
    0.49
     Greer
    0.49
     lt
    0.49
     smaller
    0.48
     bé
    0.45
    <?
    0.45
    &
    0.45
    Activations Density 0.623%

    No Known Activations