© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8452
    Prev
    Next
    INDEX
    Explanations

    statistical terms and methods used in data analysis and regression modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apimachinery
    -0.50
    BeginContext
    -0.49
    xase
    -0.48
    AddTagHelper
    -0.45
    atorul
    -0.44
     دیکھیے
    -0.44
    postIndex
    -0.43
    裟
    -0.43
    UnitTesting
    -0.42
    rophe
    -0.41
    POSITIVE LOGITS
     empirically
    0.50
     compute
    0.44
     empirical
    0.42
     computation
    0.42
     iterate
    0.42
     roll
    0.42
     leverage
    0.42
     methods
    0.41
     algorithms
    0.41
     employ
    0.41
    Activations Density 1.823%

    No Known Activations