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. 21-GEMMASCOPE-RES-16K
    6. 12483
    Prev
    Next
    INDEX
    Explanations

    terms related to protein folding and structural characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nestjs
    -0.55
     komun
    -0.55
    MethodManager
    -0.52
    gnostic
    -0.49
    све
    -0.49
     Mines
    -0.46
     useDispatch
    -0.46
     ujednoznacz
    -0.46
    Mars
    -0.46
    othelioma
    -0.45
    POSITIVE LOGITS
     molecule
    1.01
     molecules
    0.99
     molecular
    0.94
     protein
    0.93
     structure
    0.88
     proteins
    0.86
     molé
    0.83
    molecular
    0.79
     structures
    0.78
    molecule
    0.75
    Activations Density 1.643%

    No Known Activations