© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 9941
    Prev
    Next
    INDEX
    Explanations

    negations and negative constructions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Krakowie
    -0.70
    opsida
    -0.70
    SharedDtor
    -0.68
    ']:
    -0.65
    SequentialGroup
    -0.64
    agerie
    -0.64
     getItemCount
    -0.64
    CreateModel
    -0.63
     Biel
    -0.63
    []):
    -0.62
    POSITIVE LOGITS
    would
    0.80
     WOULD
    0.78
     would
    0.76
    也不会
    0.68
    也不會
    0.67
     Would
    0.67
    UrlResolution
    0.64
     WILL
    0.63
     Willoughby
    0.62
     pourrez
    0.62
    Activations Density 0.132%

    No Known Activations