© 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. 8529
    Prev
    Next
    INDEX
    Explanations

    references to sets and their components or configurations

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

    "set" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    set up, method, or of

    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
    numerusform
    -0.61
    istaa
    -0.54
    kömm
    -0.53
    ization
    -0.53
    ️
    -0.53
    hips
    -0.50
     AssemblyCompany
    -0.48
    ist
    -0.48
    الحياه
    -0.48
    ables
    -0.47
    POSITIVE LOGITS
    tled
    0.86
     aside
    0.81
    tting
    0.80
     forth
    0.78
    tableFuture
    0.78
    tling
    0.76
     up
    0.74
    tles
    0.68
    aside
    0.67
    jmp
    0.66
    Activations Density 0.136%

    No Known Activations