© 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. 14343
    Prev
    Next
    INDEX
    Explanations

    closing braces in code

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

    closing braces at the end of code blocks.

    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
    Through
    -0.36
    CopyWith
    -0.36
    Across
    -0.35
     cref
    -0.35
     enfermed
    -0.34
    Later
    -0.34
     pagină
    -0.34
     ModelExpression
    -0.34
    füh
    -0.34
    çeği
    -0.33
    POSITIVE LOGITS
     else
    1.47
    else
    1.41
     otherwise
    1.37
     Otherwise
    1.17
    Otherwise
    1.07
     Else
    1.05
    otherwise
    1.02
     ELSE
    1.00
    否则
    0.91
     OTHERWISE
    0.90
    Activations Density 0.092%

    No Known Activations