© 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. 25-GEMMASCOPE-RES-16K
    11. 274
    Prev
    Next
    INDEX
    Explanations

    instances of the word "each" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anything
    -0.78
     any
    -0.70
     ANYTHING
    -0.68
     anywhere
    -0.67
     anytime
    -0.65
    any
    -0.61
     ANY
    -0.59
    anything
    -0.58
    mergeFrom
    -0.56
     Anything
    -0.55
    POSITIVE LOGITS
     respective
    1.11
     individual
    1.10
     successive
    1.09
     einzelnen
    1.06
    individual
    0.93
     einzelne
    0.92
     individually
    0.91
    각
    0.90
     separate
    0.86
     einzeln
    0.82
    Activations Density 0.162%

    No Known Activations