© 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. 12314
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and locations

    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
     esophageal
    -0.65
     Diſ
    -0.64
     Voigt
    -0.64
     myſelf
    -0.63
     Hift
    -0.63
     Lyt
    -0.63
     Monfieur
    -0.62
     getItemCount
    -0.62
    écnicas
    -0.60
    GOTREF
    -0.60
    POSITIVE LOGITS
     Cornwall
    0.72
     Ker
    0.66
     Hel
    0.57
     Cornish
    0.56
     Gwen
    0.55
     Tre
    0.55
    Corn
    0.54
    Ker
    0.53
     Pol
    0.53
    Gwen
    0.51
    Activations Density 0.086%

    No Known Activations