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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13565
    Prev
    Next
    INDEX
    Explanations

    key terms related to police clearance and identification processes

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

    trips, visas, or PCCs

    np_acts-logits-general · gemini-2.0-flash

    confront challenge, two situations, get stamped, overseas trip

    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
     fallait
    -0.64
     tartalomajánló
    -0.56
     ${{
    -0.54
     ویکی‌پدیای
    -0.54
    WithIdentifier
    -0.53
     hanem
    -0.52
    请问
    -0.51
    Бахар
    -0.50
    Diweddarwch
    -0.50
    若干
    -0.49
    POSITIVE LOGITS
    tvguidetime
    0.78
     Notwithstanding
    0.62
     notwithstanding
    0.57
     administrations
    0.55
     conceivable
    0.55
    explicit
    0.54
    findpost
    0.54
     additionally
    0.53
    kloped
    0.53
    Rund
    0.53
    Activations Density 0.109%

    No Known Activations