© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 1080
    Prev
    Next
    INDEX
    Explanations

    terms related to prenatal medical assessments and their implications for maternal and fetal health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.65
    urysty
    -0.64
    PhysRev
    -0.54
    jura
    -0.53
     held
    -0.52
     Mast
    -0.52
    ukone
    -0.51
    MessageTagHelper
    -0.51
    UnknownFieldSet
    -0.50
    ElementException
    -0.49
    POSITIVE LOGITS
     fetal
    1.05
     maternal
    0.91
     placental
    0.91
     Fetal
    0.85
     fetus
    0.84
     placenta
    0.83
     Maternal
    0.81
     gestational
    0.77
     fet
    0.76
    pla
    0.74
    Activations Density 0.977%

    No Known Activations