© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 13491
    Prev
    Next
    INDEX
    Explanations

    mentions of birds and bird-related terminology

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

    "bird" or "birds"

    np_acts-logits-general · gemini-2.0-flash

    bird's eye view, watchers, songs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.60
     sürd
    -0.46
    Allister
    -0.45
    évaluateur
    -0.45
     Tread
    -0.45
    chränk
    -0.44
    ThroughAttribute
    -0.44
    UrlResolution
    -0.43
     Stomp
    -0.42
     CURLOPT
    -0.42
    POSITIVE LOGITS
    Bird
    0.69
     Bird
    0.67
     BIRD
    0.64
    BIRD
    0.63
     bird
    0.63
    Birds
    0.61
    bird
    0.60
     Birds
    0.60
     пти
    0.58
    birds
    0.58
    Activations Density 0.136%

    No Known Activations