© 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. 4-GEMMASCOPE-RES-16K
    11. 10871
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or repeated references to the concept of "ever."

    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
     CURIAM
    -0.70
    stdc
    -0.62
     تانيه
    -0.59
    Datuak
    -0.59
    makeConstraints
    -0.58
    ็จ
    -0.57
    bootstrapcdn
    -0.57
    ogonal
    -0.55
     חיצוניים
    -0.53
     préfé
    -0.52
    POSITIVE LOGITS
     never
    1.58
    NEVER
    1.56
     Never
    1.54
    Never
    1.54
    never
    1.51
     NEVER
    1.50
     jamais
    1.31
     jamás
    1.29
     ever
    1.28
     EVER
    1.24
    Activations Density 0.160%

    No Known Activations