© 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. 11-GEMMASCOPE-RES-16K
    11. 14109
    Prev
    Next
    INDEX
    Explanations

    phrases indicating complexities or challenges in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    เลย
    -0.69
    MigrationBuilder
    -0.58
    therefore
    -0.57
    aarrggbb
    -0.55
     sih
    -0.52
    thus
    -0.52
     therefore
    -0.51
    طلحات
    -0.51
    душка
    -0.51
    logna
    -0.51
    POSITIVE LOGITS
     nonetheless
    0.89
    それでも
    0.76
     nevertheless
    0.72
    </tfoot>
    0.72
    それにしても
    0.71
     trotzdem
    0.70
    $")
    0.62
     dennoch
    0.57
    theless
    0.57
    "):
    0.57
    Activations Density 1.825%

    No Known Activations