© 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. 14-GEMMASCOPE-RES-16K
    11. 5739
    Prev
    Next
    INDEX
    Explanations

    elements related to visual and physical descriptions

    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
     normais
    -0.36
     petitions
    -0.35
     cuidados
    -0.35
     pros
    -0.34
     Interpretation
    -0.34
     mewakili
    -0.33
     Verlust
    -0.33
     Probably
    -0.33
     länge
    -0.32
    interprétation
    -0.32
    POSITIVE LOGITS
    richTextPanel
    0.69
     Италијани
    0.60
    EndInit
    0.59
     propOrder
    0.59
    XtraEditors
    0.58
    SourceChecksum
    0.54
    PYX
    0.53
    XmlAccessType
    0.53
     createSlice
    0.52
    يميديا
    0.52
    Activations Density 0.351%

    No Known Activations