© 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. 4396
    Prev
    Next
    INDEX
    Explanations

    indicators of analytical frameworks or methods within texts

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

    document section headers and structural formatting markers.

    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
    الإنجليزية
    -0.49
    Personendaten
    -0.44
    adaptiveStyles
    -0.44
     المعيارى
    -0.44
    labelledby
    -0.41
    CompleteListener
    -0.40
    rungsseite
    -0.40
    zzleHttp
    -0.38
    consulté
    -0.38
    libft
    -0.38
    POSITIVE LOGITS
     introduction
    2.44
     Introduction
    2.28
     introductions
    2.19
    Introduction
    2.16
    introduction
    2.11
     introducción
    2.09
     INTRODUCTION
    2.00
     introductory
    1.93
    INTRODUCTION
    1.88
     intro
    1.81
    Activations Density 0.838%

    No Known Activations