© 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. 28-GEMMASCOPE-RES-16K
    11. 4131
    Prev
    Next
    INDEX
    Explanations

    interactions and identities in discussions about language and relationships

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

    Followed by a happy face emoticon

    np_acts-logits-general · gemini-2.0-flash

    expressions of laughter and amusement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.53
    pexpr
    -0.43
     kapturem
    -0.35
     +%
    -0.35
    mybatisplus
    -0.35
    ()]
    -0.35
    }\\
    -0.34
    matchCondition
    -0.33
    ]:
    -0.33
     \%$\\
    -0.33
    POSITIVE LOGITS
     lol
    1.76
     haha
    1.69
     LOL
    1.62
     hahaha
    1.54
     😂
    1.48
     hehe
    1.48
    lol
    1.42
     ;-)
    1.42
     jajaja
    1.41
    😂
    1.41
    Activations Density 0.622%

    No Known Activations