© 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. 4245
    Prev
    Next
    INDEX
    Explanations

    references to scientific literature and methodologies

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

    before commas or parentheses

    np_acts-logits-general · gemini-2.0-flash

    specific scientific concepts

    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
     lui
    -0.67
     mnie
    -0.58
    是她
    -0.58
    herself
    -0.55
     eux
    -0.55
    让她
    -0.54
    在我
    -0.53
    在她
    -0.52
    被他
    -0.52
     vuotta
    -0.52
    POSITIVE LOGITS
     there
    2.00
     it
    1.69
     they
    1.53
     we
    1.45
     the
    1.29
    there
    1.28
     everything
    1.23
     nothing
    1.20
     you
    1.14
     theres
    1.13
    Activations Density 1.079%

    No Known Activations