© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 7901
    Prev
    Next
    INDEX
    Explanations

    actions and movements related to social interactions and gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.86
    ьаж
    -0.74
     utafitiHapana
    -0.72
    ]++;
    -0.71
     '\\;'
    -0.65
     envió
    -0.60
     systemic
    -0.60
     Abp
    -0.59
    IsMutable
    -0.57
    !*\
    -0.56
    POSITIVE LOGITS
     banda
    0.49
    Bes
    0.48
     microphones
    0.47
     redor
    0.47
     micrófono
    0.46
    ervlak
    0.46
     bedside
    0.45
    flüs
    0.45
     microphone
    0.45
     bancaire
    0.44
    Activations Density 0.228%

    No Known Activations