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. 20-GEMMASCOPE-RES-16K
    6. 1224
    Prev
    Next
    INDEX
    Explanations

    data related to clinical trials, particularly focusing on treatment effectiveness and patient outcomes

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

    before medical outcomes/responses

    np_acts-logits-general · gemini-2.0-flash

    response rate progression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hog
    -0.44
    OneToMany
    -0.42
    Cancer
    -0.41
     gar
    -0.41
    det
    -0.41
     Cancer
    -0.41
    昔から
    -0.40
     ü
    -0.40
     scel
    -0.39
    zcz
    -0.38
    POSITIVE LOGITS
     Efq
    1.00
     ویکی‌پدیای
    0.82
     Chriftian
    0.82
    DockStyle
    0.82
     kaynağından
    0.82
     raiſ
    0.80
     Majefty
    0.79
     chofe
    0.78
     purpoſe
    0.78
    MLLoader
    0.77
    Activations Density 1.927%

    No Known Activations