© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5370
    Prev
    Next
    INDEX
    Explanations

    terms related to specific diseases and their associated genetic or pathological mechanisms

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

    starting with "ph", "che", "py", "li"

    np_acts-logits-general · gemini-2.0-flash

    pharyngitis, pyrexia, cholesterol, pelvic, schizophrenia

    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
    Referències
    -0.60
    دانشنامهٔ
    -0.58
    互联网档案馆
    -0.52
     imper
    -0.47
     跳转至
    -0.47
     Kort
    -0.47
     Nib
    -0.46
     Playboy
    -0.46
     nele
    -0.46
     noqa
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.76
    ChildScrollView
    0.55
    crollView
    0.53
    UIControlState
    0.52
    AnchorStyles
    0.52
    cshtml
    0.51
    发表于
    0.51
    ConverterFactory
    0.49
     Smarter
    0.47
     CURIAM
    0.47
    Activations Density 1.066%

    No Known Activations