© 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. 21-GEMMASCOPE-RES-16K
    11. 14944
    Prev
    Next
    INDEX
    Explanations

    specific phrases and technical terms related to scientific experiments and procedures in cell biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.84
    //
    -0.82
     EconPapers
    -0.72
    Rptr
    -0.70
    RectangleBorder
    -0.69
    +#+#
    -0.68
    MigrationBuilder
    -0.67
    protoimpl
    -0.67
    rungsseite
    -0.66
    ंदीखरीदारी
    -0.65
    POSITIVE LOGITS
     selama
    1.19
     لمدة
    1.12
     for
    1.10
     briefly
    0.92
     until
    0.92
     forever
    0.92
     indefinitely
    0.88
     течение
    0.88
    for
    0.83
     протягом
    0.82
    Activations Density 0.692%

    No Known Activations