© 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. 13227
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific user or subject in discussions

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

    usernames or author names in chat messages and forum posts.

    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
    脚注の使い方
    -0.58
    StructEnd
    -0.54
    sidemargin
    -0.54
    
    -0.53
     Wikimedijinoj
    -0.49
     հղումներ
    -0.48
    Datuak
    -0.48
    клопе
    -0.48
    FieldBuilder
    -0.47
    DECREF
    -0.47
    POSITIVE LOGITS
     An
    0.48
     AN
    0.43
    An
    0.41
     ancient
    0.39
    ########.
    0.35
    南浔
    0.34
     unattended
    0.33
     الأس
    0.32
     अन
    0.31
     atractiva
    0.31
    Activations Density 0.128%

    No Known Activations