© 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. 35-GEMMASCOPE-RES-16K
    6. 6731
    Prev
    Next
    INDEX
    Explanations

    medical terminologies and procedures related to patient monitoring and anesthesia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unsolved
    -0.43
    养
    -0.40
    ronique
    -0.37
    一亮
    -0.37
     старости
    -0.37
     cured
    -0.35
    镶
    -0.35
     sepol
    -0.35
     curing
    -0.34
     exploding
    -0.34
    POSITIVE LOGITS
     client
    0.62
     klien
    0.60
     Client
    0.56
     CLIENT
    0.53
     שוליים
    0.52
    Client
    0.49
    client
    0.48
     aus
    0.48
     Clients
    0.48
     clients
    0.48
    Activations Density 0.996%

    No Known Activations