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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12671
    Prev
    Next
    INDEX
    Explanations

    references to specific plant species and natural environments

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

    Preceding numbers

    np_acts-logits-general · gemini-2.0-flash

    country names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diweddarwch
    -0.63
    rrggbb
    -0.59
    ofluor
    -0.57
     ingresar
    -0.55
     econômica
    -0.54
     argint
    -0.52
     Azt
    -0.52
     secretions
    -0.52
     Juneau
    -0.52
     Muscat
    -0.52
    POSITIVE LOGITS
     Country
    0.65
     countryside
    0.63
     countryman
    0.59
     hed
    0.58
     RSP
    0.57
    RSP
    0.57
    Country
    0.56
     SSS
    0.56
     Quanto
    0.55
     COUNTRY
    0.55
    Activations Density 0.281%

    No Known Activations