© 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. 31-GEMMASCOPE-RES-16K
    6. 8660
    Prev
    Next
    INDEX
    Explanations

    error handling and conditional statements in programming code

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

    error handling patterns in Go code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToAction
    -0.36
    colgroup
    -0.35
    heça
    -0.34
    WebpackPlugin
    -0.33
    Enllaces
    -0.32
     suple
    -0.32
    LocationManager
    -0.32
    PropertyChanging
    -0.31
     useless
    -0.31
    abetes
    -0.31
    POSITIVE LOGITS
    Autoritní
    0.66
    wantErr
    0.56
    ftagPool
    0.56
    URLException
    0.50
    Derbyniad
    0.49
     Wolfs
    0.47
    nef
    0.47
     المعيارى
    0.46
    meneu
    0.46
    MessageTagHelper
    0.45
    Activations Density 0.128%

    No Known Activations