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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2797
    Prev
    Next
    INDEX
    Explanations

    information related to insect biology, specifically focusing on life cycles and species characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttino
    -0.58
     dolphins
    -0.57
     forState
    -0.53
     dolphin
    -0.53
    rungsseite
    -0.53
     Gato
    -0.51
    dymyr
    -0.49
    cannon
    -0.49
    Rade
    -0.48
     Сме
    -0.48
    POSITIVE LOGITS
     insect
    1.25
     insects
    1.17
     Insect
    1.15
     bugs
    1.14
     flies
    1.09
     fly
    1.07
     larvae
    1.07
     larva
    1.06
    Insect
    1.05
     bug
    1.04
    Activations Density 0.531%

    No Known Activations