© 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. 20-GEMMASCOPE-RES-16K
    6. 2108
    Prev
    Next
    INDEX
    Explanations

    numerical representations and sequences related to data sets

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

    technical and scientific document metadata and citation references.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    technical markup and reference identifiers featuring the digit 0 and hyphenated numeric codes in academic text.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the digit "0" in technical or scientific documents, particularly in reference citations, numerical identifiers, and measurements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     the
    -0.70
    omenclature
    -0.50
     assist
    -0.49
    </tr>
    -0.49
     adipis
    -0.48
     pelúcia
    -0.47
    subpackage
    -0.47
    <bos>
    -0.47
     (
    -0.47
    siąż
    -0.47
    POSITIVE LOGITS
    0
    1.22
    0
    0.59
    ০
    0.58
    ۰
    0.57
    Zero
    0.56
     cero
    0.56
     zéro
    0.56
     ZERO
    0.55
     Zero
    0.55
     zero
    0.53
    Activations Density 0.922%

    No Known Activations