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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6331
    Prev
    Next
    INDEX
    Explanations

    terms related to communication channels and media formats

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

    preceding "casts" or related to news broadcasts

    np_acts-logits-general · gemini-2.0-flash

    news broadcasts and segments

    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
    ات
    -0.60
    ally
    -0.59
    ALLY
    -0.58
    gehalt
    -0.57
    ITY
    -0.55
    ︎
    -0.51
    ACGIH
    -0.51
    ity
    -0.50
    binaan
    -0.50
    اتی
    -0.50
    POSITIVE LOGITS
    board
    1.06
    room
    1.06
    work
    1.05
    point
    1.02
    boat
    1.00
    coat
    0.99
    house
    0.97
    book
    0.96
    line
    0.96
    fall
    0.95
    Activations Density 3.181%

    No Known Activations