© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 13023
    Prev
    Next
    INDEX
    Explanations

    references to race and related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.54
    parsedMessage
    -0.52
    emlrt
    -0.52
    ʖ
    -0.47
    期刊论文
    -0.43
     decote
    -0.41
    ۜ
    -0.40
    ✨:
    -0.40
    âmara
    -0.40
    ⮕
    -0.39
    POSITIVE LOGITS
     relation
    2.63
     relationship
    2.58
     relations
    2.55
     Relation
    2.38
    relation
    2.38
     relationships
    2.33
    Relation
    2.31
     Relations
    2.28
     Relationship
    2.27
    relationship
    2.27
    Activations Density 0.719%

    No Known Activations