© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14465
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with significant levels or scores

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

    elements of mathematical expressions, especially standalone numbers and exponentiation within algebraic simplification contexts.

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

    numerical digits, especially when they appear in mathematical expressions or formal notation.

    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
    -0.59
    ’
    -0.41
     […]
    -0.40
    '
    -0.40
    mathrm
    -0.38
    lo
    -0.36
    amp
    -0.35
    GL
    -0.35
    <tbody>
    -0.34
    LO
    -0.34
    POSITIVE LOGITS
     CreateTagHelper
    1.28
     Мексичка
    1.20
     للاسماء
    1.14
     Савезне
    1.14
    AndEndTag
    1.01
    Personendaten
    0.99
     ModelExpression
    0.98
    TagMode
    0.97
     tartalomajánló
    0.93
    AddTagHelper
    0.93
    Activations Density 0.000%
    No Known Activations