© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6767
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations and names related to natural and cultural features

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

    proper nouns and names of specific locations or geographic features.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wrocław
    -0.54
     vettor
    -0.51
     prodig
    -0.49
     Yucatán
    -0.48
    principalColumn
    -0.48
    typeorm
    -0.48
    bondale
    -0.48
     sternum
    -0.48
    ofition
    -0.48
     Penang
    -0.48
    POSITIVE LOGITS
     surla
    0.37
     acres
    0.36
     benach
    0.35
     नाम
    0.33
     notamment
    0.33
     Administr
    0.33
     ObjectParameter
    0.32
     numerus
    0.32
     neighbouring
    0.32
     Settlement
    0.31
    Activations Density 0.146%

    No Known Activations