© 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. 12-GEMMASCOPE-RES-16K
    11. 4309
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical notation and scientific expressions

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

    Greek letters and mathematical indices in LaTeX equations (particularly "mu", "rho", "abc" and similar symbolic notation).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    complex LaTeX-formatted physics equations with tensors and indices, especially expressions rich in Greek symbols, superscripts/subscripts, and TeX control sequences.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.77
    WithIOException
    -0.73
     تكبرها
    -0.66
    PostInfinity
    -0.65
    WireFormatLite
    -0.64
     Autorizaciones
    -0.62
     Taktlose
    -0.62
     resourceCulture
    -0.61
    expandindo
    -0.61
    sizeCache
    -0.60
    POSITIVE LOGITS
    pub
    0.34
    ESTRA
    0.33
     Col
    0.31
    N
    0.31
     pick
    0.31
     pr
    0.30
     iParam
    0.30
     inf
    0.30
    raquo
    0.29
     C
    0.29
    Activations Density 1.000%

    No Known Activations