Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65819
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to quantum mechanics and tunneling phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useSelector
    -0.35
     وصلة
    -0.35
    MemoryWarning
    -0.35
    новништво
    -0.35
     FishBase
    -0.34
     vectorielles
    -0.34
    matico
    -0.34
     useDispatch
    -0.33
     phối
    -0.33
    ufnahme
    -0.32
    POSITIVE LOGITS
     صوتيه
    0.84
     tunneling
    0.74
     tunnel
    0.70
     tunne
    0.68
    tunnel
    0.66
     túnel
    0.65
     Tunnel
    0.63
    Tunnel
    0.61
     tunnels
    0.60
    tun
    0.57
    Activations Density 0.303%

    No Known Activations