© 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. 20-GEMMASCOPE-RES-16K
    11. 15281
    Prev
    Next
    INDEX
    Explanations

    instances of negation and conditions related to decision-making

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

    Comes before adverbs like 'simply', 'just', or 'merely'

    np_acts-logits-general · gemini-2.0-flash

    just or simply

    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
     >=",
    -0.59
     DialogInterface
    -0.58
    __*/
    -0.48
     فريبيس
    -0.48
    ureusement
    -0.48
    сми
    -0.46
    migrationBuilder
    -0.46
    зин
    -0.46
    tså
    -0.45
    おお
    -0.45
    POSITIVE LOGITS
     simply
    3.41
    simply
    3.00
     simplemente
    2.98
     merely
    2.92
     just
    2.89
     semplicemente
    2.71
    Simply
    2.64
     просто
    2.63
     simplement
    2.61
     Simply
    2.59
    Activations Density 0.884%

    No Known Activations