© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 11918
    Prev
    Next
    INDEX
    Explanations

    modal verbs and references to possibility or impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.28
     Efq
    -1.23
     فريبيس
    -1.21
    ImageContext
    -1.21
    NUMX
    -1.16
    IntoConstraints
    -1.11
     الدولى
    -1.10
     ddelweddau
    -1.07
    tvguidetime
    -1.07
     ComVisible
    -1.06
    POSITIVE LOGITS
    ↵↵
    0.66
    <eos>
    0.60
    j
    0.58
    In
    0.57
     is
    0.56
    '
    0.53
    br
    0.53
     It
    0.53
     
    0.52
    se
    0.52
    Activations Density 0.119%

    No Known Activations