© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 9806
    Prev
    Next
    INDEX
    Explanations

    elements related to inscriptions and their physical attributes, especially in stone and molded materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.61
    IANGLES
    -0.60
    jsxFileName
    -0.57
    zzleHttp
    -0.57
     BoxFit
    -0.57
     snippetHide
    -0.54
     tartalomajánló
    -0.52
     MainAxisSize
    -0.51
     Salom
    -0.51
     trous
    -0.50
    POSITIVE LOGITS
     sculpt
    0.67
    scul
    0.65
     sculpted
    0.63
     carved
    0.63
     sculpting
    0.62
     Sculpt
    0.59
     carving
    0.59
     carvings
    0.57
    Scul
    0.56
     sculptures
    0.54
    Activations Density 0.275%

    No Known Activations