© 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. 8429
    Prev
    Next
    INDEX
    Explanations

    specific numerical metrics and quantities in various contexts

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

    relative position or direction

    np_acts-logits-general · gemini-2.0-flash

    relative positions and quantities

    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
    Referencer
    -0.52
    ratto
    -0.47
    円で
    -0.47
    properly
    -0.46
    حوالہ
    -0.46
     ويكيپيديا
    -0.46
    PRWEB
    -0.45
    djangoproject
    -0.44
     raste
    -0.43
    商品説明
    -0.42
    POSITIVE LOGITS
     away
    1.38
     ahead
    1.03
     below
    0.99
     above
    0.99
     AWAY
    0.98
    away
    0.96
     Away
    0.92
     apart
    0.85
    Away
    0.85
     BELOW
    0.82
    Activations Density 0.247%

    No Known Activations