© 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. 24-GEMMASCOPE-RES-16K
    6. 4225
    Prev
    Next
    INDEX
    Explanations

    references to entities or topics that contain the substring "Al"

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

    Follows "al" or "Al" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    al- prefix and related suffixes

    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
     estimés
    -0.62
    migrationBuilder
    -0.55
    Further
    -0.54
    agoza
    -0.54
     further
    -0.54
     Further
    -0.53
    izoen
    -0.53
    wikimedia
    -0.52
     createSprite
    -0.52
     AssemblyTitle
    -0.50
    POSITIVE LOGITS
    querque
    0.62
     wikipagina
    0.62
    θεια
    0.58
    yordu
    0.56
    orithms
    0.55
    native
    0.54
     Frequencies
    0.53
     pherom
    0.52
    inosi
    0.52
    aska
    0.52
    Activations Density 0.221%

    No Known Activations