© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9452
    Prev
    Next
    INDEX
    Explanations

    references to "nose" or related concepts associated with smelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saka
    -0.65
     Wiktionnaire
    -0.64
     Haarlem
    -0.62
    requipa
    -0.60
     Polyp
    -0.59
     صوتيه
    -0.57
    RegistryLite
    -0.57
     Nijmegen
    -0.57
     allAfrica
    -0.57
    Демографія
    -0.56
    POSITIVE LOGITS
     nose
    1.30
     Nose
    0.95
    nose
    0.94
     noses
    0.94
    Nose
    0.88
     USB
    0.69
     nariz
    0.66
    تقاوى
    0.63
    USB
    0.61
    bis
    0.56
    Activations Density 0.100%

    No Known Activations