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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3146
    Prev
    Next
    INDEX
    Explanations

    discussions related to patient groups in clinical studies

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

    study groups (A, B, C)

    np_acts-logits-general · gemini-2.0-flash

    groups letters A, B, C, respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     another
    -0.51
    strerror
    -0.49
    asztal
    -0.46
    nitts
    -0.45
     nakalista
    -0.43
    titious
    -0.43
    uidado
    -0.43
     который
    -0.42
    []=$
    -0.42
     Ausgang
    -0.42
    POSITIVE LOGITS
    Datuak
    1.02
     both
    1.01
    both
    0.93
     Messrs
    0.91
     jScrollPane
    0.87
     Roskov
    0.87
    分别是
    0.86
    enumii
    0.86
    UserScript
    0.85
    Both
    0.84
    Activations Density 1.091%

    No Known Activations