© 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 - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 10013
    Prev
    Next
    INDEX
    Explanations

    references to birds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •birdbirdbirdbirdbirdbird

    No Comments

    Negative Logits
    LabelTagHelper
    -0.78
    BeginInit
    -0.76
    Parcelize
    -0.75
     '\\;'
    -0.73
    featureID
    -0.71
    TagMode
    -0.69
    PreExecute
    -0.66
    pushFollow
    -0.65
    Kaieteur
    -0.63
    FailureListener
    -0.62
    POSITIVE LOGITS
     Palestinians
    0.64
     Blues
    0.60
    Blues
    0.58
     mono
    0.55
     hiker
    0.54
     fades
    0.54
     pedestrians
    0.54
     Physik
    0.53
    mono
    0.53
    Mono
    0.53
    Activations Density 0.101%

    No Known Activations