© 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. 14-GEMMASCOPE-RES-16K
    6. 8049
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or causality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.79
    Otis
    -0.67
    fören
    -0.66
    odotus
    -0.65
     vectorielles
    -0.65
     isoliert
    -0.65
     tentativo
    -0.64
     Huns
    -0.63
     paramString
    -0.63
    cámara
    -0.62
    POSITIVE LOGITS
    abo
    0.75
    have
    0.70
    — 
    0.69
    曖昧さ回避
    0.68
    ReusableCell
    0.65
    MathML
    0.64
    × 
    0.63
    earlier
    0.62
     Audiodateien
    0.62
    *}
    0.61
    Activations Density 0.101%

    No Known Activations