© 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. 25-GEMMASCOPE-RES-16K
    6. 15419
    Prev
    Next
    INDEX
    Explanations

    topics related to surgical procedures and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bitField
    -0.48
     Houſe
    -0.48
     ſtate
    -0.45
    rungsseite
    -0.43
     ſtre
    -0.42
     pleaſure
    -0.42
     themſelves
    -0.42
    ſelves
    -0.42
     houſe
    -0.42
     ftate
    -0.42
    POSITIVE LOGITS
     surgical
    0.97
     surgery
    0.95
     surgically
    0.93
     Surgical
    0.84
    surgery
    0.82
    Surgery
    0.82
     surgeons
    0.80
     Surgery
    0.78
     surgeries
    0.78
     implant
    0.77
    Activations Density 1.101%

    No Known Activations