© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1898
    Prev
    Next
    INDEX
    Explanations

    instances of formal declarations or announcements

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

    Code or short phrases ending in certain punctuation

    np_acts-logits-general · gemini-2.0-flash

    scientific and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     läßt
    -0.61
     (;;)
    -0.55
     Schluß
    -0.54
     muß
    -0.51
     idéia
    -0.50
     autorité
    -0.50
     plumas
    -0.50
     firme
    -0.50
    /*++
    -0.49
     daß
    -0.49
    POSITIVE LOGITS
    ########.
    1.72
    :+:
    1.35
    libft
    1.29
    #+#
    1.17
    Datuak
    1.16
    expandindo
    1.01
    Билгалдахарш
    0.99
    ::::::::
    0.94
    GraphicsUnit
    0.76
    mlx
    0.76
    Activations Density 0.063%

    No Known Activations