© 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. 21-GEMMASCOPE-RES-16K
    6. 6095
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.06
    GTCX
    -0.77
    astéro
    -0.73
    ()?;
    -0.73
     myſelf
    -0.66
    oneofs
    -0.65
    期刊论文
    -0.63
    exitRule
    -0.61
    ⓧ
    -0.61
     Madura
    -0.61
    POSITIVE LOGITS
     even
    0.68
    MemoryWarning
    0.68
     they
    0.64
    even
    0.63
    onViewCreated
    0.61
     there
    0.60
    ScopeManager
    0.58
     bahkan
    0.55
     he
    0.54
     it
    0.54
    Activations Density 0.021%

    No Known Activations