© 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. 2-GEMMASCOPE-RES-16K
    11. 14705
    Prev
    Next
    INDEX
    Explanations

    terms related to associations and comparisons in scientific studies, particularly in the context of cancer research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     déclen
    -0.56
     vostri
    -0.56
    strncpy
    -0.52
    urlpatterns
    -0.50
    appcompat
    -0.50
    {}/
    -0.49
    ỡng
    -0.48
    Lähteet
    -0.48
    liothèque
    -0.48
    clearTimeout
    -0.47
    POSITIVE LOGITS
    SPATH
    0.68
     isComment
    0.64
    клопе
    0.63
    RenderAtEndOf
    0.62
    Tikang
    0.62
    RegressionTest
    0.58
    PerformLayout
    0.58
     становника
    0.56
    WriteTagHelper
    0.55
    ("$.
    0.54
    Activations Density 1.170%

    No Known Activations