© 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. 1585
    Prev
    Next
    INDEX
    Explanations

    references to specific challenges or initiatives, particularly those named "Challenge Me"

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

    the phrase "Challenge Me" as a proper noun or intervention name.

    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
    s
    -0.31
    *
    -0.31
    ="
    -0.29
    r
    -0.26
    0
    -0.25
     ISNI
    -0.24
    ns
    -0.24
    9
    -0.23
    ↵↵
    -0.23
     Socialista
    -0.23
    POSITIVE LOGITS
     Challenge
    1.05
    Challenge
    0.96
     CHALLENGE
    0.93
     Chall
    0.93
    challenge
    0.91
    ALLENGE
    0.88
     Challenges
    0.87
     queſta
    0.86
     challenge
    0.85
     challeng
    0.84
    Activations Density 0.105%

    No Known Activations