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. 5-GEMMASCOPE-RES-16K
    6. 11025
    Prev
    Next
    INDEX
    Explanations

    terms related to nasal conditions and anatomical features related to airway and sinus health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ons
    -0.54
     buty
    -0.52
     touch
    -0.51
     Anch
    -0.50
     tardi
    -0.50
     Jasper
    -0.50
     onshore
    -0.49
     gren
    -0.49
     posi
    -0.49
    stander
    -0.49
    POSITIVE LOGITS
     tunnel
    1.08
     tunnels
    1.03
     Cave
    1.02
    tunnel
    1.00
     Tunnel
    1.00
     caves
    0.96
     cave
    0.96
    Tunnel
    0.93
    Cave
    0.92
     Caves
    0.91
    Activations Density 0.615%

    No Known Activations