© 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. 8072
    Prev
    Next
    INDEX
    Explanations

    terms related to specific medical conditions and complications

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

    medical terms and descriptions related to serious health conditions, particularly inflammatory and autoimmune diseases.

    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
     platy
    -0.56
    AutoScaleMode
    -0.52
     umbi
    -0.51
     invis
    -0.51
     navel
    -0.50
     smiley
    -0.49
     heartbeat
    -0.48
     clickable
    -0.48
     smog
    -0.47
     deuter
    -0.47
    POSITIVE LOGITS
     Kriterien
    0.50
     usually
    0.45
     suele
    0.43
     meestal
    0.42
     semejante
    0.42
     frecuentemente
    0.41
    pośred
    0.40
     leren
    0.39
     재
    0.39
     often
    0.39
    Activations Density 1.364%

    No Known Activations