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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1836
    Prev
    Next
    INDEX
    Explanations

    terms related to reliability and evaluation in clinical methodologies

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

    "Inter" or "intra" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    between, within, and across

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NullException
    -0.48
    ็ม
    -0.46
    yttää
    -0.42
    чан
    -0.41
     đèn
    -0.41
     ويكيپيديا
    -0.40
    nyx
    -0.40
     parado
    -0.39
    : 
    -0.38
     Où
    -0.38
    POSITIVE LOGITS
     intra
    1.74
     between
    1.55
    intra
    1.53
     inter
    1.52
    Intra
    1.46
     within
    1.45
     Intra
    1.44
     WITHIN
    1.42
     между
    1.39
    within
    1.37
    Activations Density 0.767%

    No Known Activations