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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8754
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to toys and action figures

    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
    envolvimento
    -0.53
    󠁿
    -0.52
    cetin
    -0.52
    writerow
    -0.51
    semibold
    -0.49
     diamants
    -0.48
    Subview
    -0.48
     WebApplication
    -0.48
     tenda
    -0.48
     schermata
    -0.47
    POSITIVE LOGITS
     toy
    1.37
     figurine
    1.36
     figurines
    1.35
     dolls
    1.33
     doll
    1.27
     figure
    1.26
     toys
    1.24
     figures
    1.20
     statue
    1.08
    figure
    1.08
    Activations Density 0.155%

    No Known Activations