© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10902
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or the absence of something

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

    Comes before "use", "know", "discussed", "carried", or "collect"

    np_acts-logits-general · gemini-2.0-flash

    not followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faudrait
    -0.38
     niech
    -0.36
     tantôt
    -0.35
    almost
    -0.35
     voici
    -0.35
     zwar
    -0.33
    不斷
    -0.33
     vooral
    -0.32
     především
    -0.31
     dopiero
    -0.31
    POSITIVE LOGITS
     necessarily
    0.79
     MainAxisSize
    0.71
    脚注の使い方
    0.67
     appreciable
    0.66
     Normdatei
    0.66
    MigrationBuilder
    0.66
    necessarily
    0.65
     ویکی‌آمباردا
    0.65
     appreciably
    0.64
     interfere
    0.63
    Activations Density 0.939%

    No Known Activations