© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6261
    Prev
    Next
    INDEX
    Explanations

    structured code blocks or segments in programming language syntax

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

    whitespace and indentation patterns in Java getter method implementations.

    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
     autorytatywna
    -1.00
     uLocal
    -0.79
    Return
    -0.79
    AddTagHelper
    -0.76
     ब्रेकडाउन
    -0.73
     Returning
    -0.72
     Return
    -0.71
    domada
    -0.70
     RETURN
    -0.69
    returning
    -0.69
    POSITIVE LOGITS
     is
    0.54
     are
    0.50
     przeznac
    0.43
     být
    0.42
     be
    0.41
     mercancías
    0.40
     étrangères
    0.40
    pantalón
    0.39
    เป็น
    0.39
     hırka
    0.38
    Activations Density 0.078%

    No Known Activations