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. 17-GEMMASCOPE-RES-16K
    6. 6216
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and treatments involving drugs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    let
    -0.47
     ibunya
    -0.45
    izaron
    -0.44
    age
    -0.42
     genoux
    -0.40
     écrit
    -0.40
     tiền
    -0.39
     istrinya
    -0.39
     ViewGroup
    -0.38
    nă
    -0.37
    POSITIVE LOGITS
     participants
    1.21
     users
    1.20
     dwellers
    1.06
     attendees
    1.03
     recipients
    1.02
    participants
    0.99
     occupants
    0.98
     sufferers
    0.96
     adherents
    0.96
     victims
    0.94
    Activations Density 0.707%

    No Known Activations