© 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. 5440
    Prev
    Next
    INDEX
    Explanations

    special formatting or structural elements within the text

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

    Follows specific words or non-English tokens

    np_acts-logits-general · gemini-2.0-flash

    information via

    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
    󠁢
    -0.55
    webtoken
    -0.49
     Efq
    -0.49
     InkWell
    -0.49
     démo
    -0.48
    HEAST
    -0.47
    ாம்
    -0.47
    ambién
    -0.46
    neurial
    -0.46
     ſhould
    -0.46
    POSITIVE LOGITS
    تقاوى
    0.94
    GEBURTSDATUM
    0.94
    Rüyada
    0.88
    sizeCache
    0.83
    gameserver
    0.82
    CodedInputStream
    0.81
    دانشنامهٔ
    0.80
    featureID
    0.77
     Vikipedi
    0.76
     '\\;'
    0.75
    Activations Density 0.543%

    No Known Activations