© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27415
    Prev
    Next
    INDEX
    Explanations

    references to birds or bird-related concepts

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

    birds and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]";
    -0.97
    >");
    
    -0.95
     pleaſure
    -0.89
     himſelf
    -0.86
     themſelves
    -0.86
     poffe
    -0.84
     reaſon
    -0.83
    $")
    -0.83
     purpoſe
    -0.82
     poffible
    -0.82
    POSITIVE LOGITS
     Bird
    1.36
     Birds
    1.33
     birds
    1.27
     BIRD
    1.23
    Bird
    1.23
    Birds
    1.21
     bird
    1.21
    bird
    1.11
    birds
    1.07
     BIRDS
    1.03
    Activations Density 0.008%

    No Known Activations