© 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. 12536
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lack of existence or presence

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

    "such" follows a negative statement

    np_acts-logits-general · gemini-2.0-flash

    no such

    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
    Hauptartikel
    -0.54
    devším
    -0.54
    těte
    -0.51
     endwhile
    -0.49
    intenant
    -0.48
    Спасылкі
    -0.47
    neté
    -0.47
    NameInMap
    -0.45
    hoeddwyd
    -0.45
    obbies
    -0.44
    POSITIVE LOGITS
     such
    2.73
    Such
    2.28
     Such
    2.23
    such
    2.20
     SUCH
    1.91
     solche
    1.84
    这样的
    1.84
     solchen
    1.74
     چنین
    1.73
    這樣的
    1.68
    Activations Density 0.818%

    No Known Activations