Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 6723
    Prev
    Next
    INDEX
    Explanations

    descriptions of supportive and comfortable undergarments, particularly sports bras

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodeAttribute
    -0.53
     Civil
    -0.52
    contentLoaded
    -0.52
    Civil
    -0.51
     livers
    -0.51
     nematode
    -0.49
    oxone
    -0.49
    Organized
    -0.48
    fachada
    -0.48
    organized
    -0.47
    POSITIVE LOGITS
     comfort
    0.92
    Comfort
    0.91
    comfort
    0.86
     Comfort
    0.86
     COMFORT
    0.76
     comfortable
    0.75
     confortable
    0.74
     الرياضيه
    0.74
     ergonom
    0.72
     discomfort
    0.71
    Activations Density 0.220%

    No Known Activations