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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6367
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships involving equations and parameters related to scientific data

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

    scientific notation and special characters in academic or mathematical text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁮
    -0.82
     snippetHide
    -0.75
    AndroidJUnit
    -0.67
    󠁴
    -0.63
    󠁬
    -0.59
     كومونز
    -0.59
    GEBURTS
    -0.58
    <bos>
    -0.57
    webElementXpaths
    -0.56
     Utf
    -0.55
    POSITIVE LOGITS
     enfans
    0.61
     Wikiseite
    0.56
    Demikian
    0.45
     Putih
    0.42
    šanās
    0.41
     Grüsse
    0.41
     Könige
    0.41
     Kebijakan
    0.41
     Khusus
    0.40
    Danke
    0.40
    Activations Density 2.421%

    No Known Activations