© 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. 16-GEMMASCOPE-RES-16K
    11. 10143
    Prev
    Next
    INDEX
    Explanations

    mathematical and statistical terminology related to conditions and theorems in estimators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.74
    featureID
    -0.72
    saraba
    -0.71
    MessageTagHelper
    -0.71
    GOTREF
    -0.70
     صوتيه
    -0.68
    MethodManager
    -0.67
    twimg
    -0.66
    Referencies
    -0.64
    outWeight
    -0.63
    POSITIVE LOGITS
     Besch
    0.33
    genossen
    0.32
    ینده
    0.32
     sentence
    0.30
     remains
    0.30
     title
    0.30
    Địa
    0.29
     proceedings
    0.29
    kapnya
    0.29
     tracks
    0.29
    Activations Density 1.054%

    No Known Activations