© 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. 20-GEMMASCOPE-RES-16K
    11. 387
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the word "one," often indicating a singular focus or idea

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

    Follows the word "One"

    np_acts-logits-general · gemini-2.0-flash

    one thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.62
    InstanceState
    -0.58
    íslu
    -0.53
     respectively
    -0.52
     تضيفلها
    -0.52
     ModelExpression
    -0.52
     Meksiku
    -0.49
    DataAnnotations
    -0.49
    /*!
    -0.48
    ActionMode
    -0.46
    POSITIVE LOGITS
     thing
    0.90
     can
    0.89
     reason
    0.88
     could
    0.88
     must
    0.86
     cannot
    0.84
     voordeel
    0.78
     important
    0.78
     may
    0.74
     كومونز
    0.73
    Activations Density 0.119%

    No Known Activations