© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 6128
    Prev
    Next
    INDEX
    Explanations

    elements related to technology, specifically in connection with data handling, processing, and system requirements

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

    conditional statements or phrases where you/one could or would do something, particularly in technical explanations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the pronoun "you" in direct address or instructional contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.56
    httphttps
    -0.42
     فريبيس
    -0.38
     calendriers
    -0.36
    ]='\
    -0.36
    帖最后由
    -0.35
     ویکی‌پدیای
    -0.35
    ########.
    -0.35
    bakan
    -0.34
    rscheinlich
    -0.34
    POSITIVE LOGITS
     can
    2.77
     could
    1.87
     peuvent
    1.67
     можно
    1.66
     dapat
    1.66
    可以
    1.61
     pouvez
    1.60
     può
    1.59
     bisa
    1.59
     possono
    1.58
    Activations Density 3.162%

    No Known Activations