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. 24-GEMMASCOPE-RES-16K
    6. 8462
    Prev
    Next
    INDEX
    Explanations

    symptoms related to various health conditions and emotional states

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

    Symptoms or side effects of medical conditions

    np_acts-logits-general · gemini-2.0-flash

    symptoms of illness or distress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.68
    WebElementEntity
    -0.61
    osamente
    -0.61
    Gc
    -0.58
    ⓧ
    -0.57
    oneofs
    -0.57
     utafitiHapana
    -0.56
    มาะ
    -0.54
    enumii
    -0.54
    unikasi
    -0.53
    POSITIVE LOGITS
     difficulty
    0.82
    Difficulty
    0.73
    difficulty
    0.72
     dizziness
    0.71
     increased
    0.71
     Difficulty
    0.69
     loss
    0.69
     decreased
    0.68
     fatigue
    0.67
     shortness
    0.66
    Activations Density 0.328%

    No Known Activations