© 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. 8-GEMMASCOPE-RES-16K
    6. 4974
    Prev
    Next
    INDEX
    Explanations

    negations or qualifiers that imply uncertainty or conditions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Superhost
    -0.55
    RTEE
    -0.49
     somewhat
    -0.49
    Autoritní
    -0.48
     rather
    -0.47
    sistant
    -0.46
     consistently
    -0.45
     evidently
    -0.45
     apparently
    -0.45
    erweise
    -0.43
    POSITIVE LOGITS
     religieuses
    0.83
    不一定
    0.75
    IntoConstraints
    0.73
    anskje
    0.72
    未必
    0.72
     démocr
    0.72
    seamnă
    0.71
     étanche
    0.69
     réflé
    0.67
     religieuse
    0.67
    Activations Density 0.330%

    No Known Activations