© 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. 8686
    Prev
    Next
    INDEX
    Explanations

    programming or code comments indicating tasks to be done (TODOs)

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

    TODO comments in 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
    それだけ
    -0.39
     pinulongan
    -0.38
    writeFieldEnd
    -0.37
    évaluateur
    -0.36
     ―――――
    -0.34
    Oto
    -0.34
     HelloWorld
    -0.33
     fraternity
    -0.33
    ContentAsync
    -0.33
     Ayah
    -0.32
    POSITIVE LOGITS
     refactor
    0.67
     reworked
    0.61
     handled
    0.60
     bug
    0.60
     workaround
    0.59
     awkward
    0.58
     hack
    0.57
    tagHelperRunner
    0.57
    uidado
    0.56
     penanganan
    0.56
    Activations Density 1.127%

    No Known Activations