Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7881
    Prev
    Next
    INDEX
    Explanations

    references to iron and related biochemical processes

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

    "F." followed by "cylindrus"

    np_acts-logits-general · gemini-2.0-flash

    F. cylindrus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.79
     finite
    -0.70
    styrelsen
    -0.68
    verwijspagina
    -0.67
    ContentAlignment
    -0.66
     federal
    -0.65
     BorderRadius
    -0.65
    signia
    -0.63
    íncia
    -0.63
    federal
    -0.62
    POSITIVE LOGITS
    fortawesome
    0.78
     getF
    0.68
     accompli
    0.61
     Fighters
    0.61
     Falcons
    0.54
     FSU
    0.54
    ftagPool
    0.53
    FSA
    0.53
    Bronnen
    0.52
    Примітки
    0.51
    Activations Density 2.114%

    No Known Activations