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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 4853
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to heart conditions and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.69
     Benedetto
    -0.61
    PreferredItem
    -0.59
     protoimpl
    -0.57
    argli
    -0.51
    rateful
    -0.50
    kran
    -0.50
     anak
    -0.48
    oore
    -0.48
     Miocene
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.59
     فريبيس
    0.53
    PyExc
    0.52
     ErrInvalid
    0.49
     AspNetCore
    0.49
     Schichten
    0.48
     CommonModule
    0.47
    alities
    0.46
    MENAFN
    0.46
    useNewUrlParser
    0.46
    Activations Density 0.082%

    No Known Activations