© 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. 11998
    Prev
    Next
    INDEX
    Explanations

    issues related to problem-solving or malfunctioning systems

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

    problem descriptions and technical issue statements.

    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
     Administrativna
    -0.47
    onViewCreated
    -0.43
     defStyleAttr
    -0.42
    readAs
    -0.41
    ilangkan
    -0.41
    astify
    -0.41
    wertes
    -0.41
    angliski
    -0.40
    prüche
    -0.40
    RTEX
    -0.39
    POSITIVE LOGITS
     problem
    3.38
    problem
    3.11
     problems
    2.98
    Problem
    2.92
     Problem
    2.88
     problema
    2.88
     problème
    2.75
     PROBLEM
    2.72
    problems
    2.67
     probleem
    2.67
    Activations Density 1.355%

    No Known Activations