© 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. 1014
    Prev
    Next
    INDEX
    Explanations

    keywords associated with dimensions, structures, or concepts of memory and projection

    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
     NSCoder
    -0.93
     ་་
    -0.93
    ConstraintMaker
    -0.91
    NUMX
    -0.91
    OGND
    -0.88
    yntaxException
    -0.86
    Kesimpulan
    -0.84
    __':
    
    -0.84
    BeginContext
    -0.83
     Majefty
    -0.83
    POSITIVE LOGITS
     is
    0.68
    ↵
    0.59
    ,
    0.57
     of
    0.56
    ↵↵
    0.55
    &
    0.55
    <sub>
    0.55
     <
    0.55
    is
    0.54
    ?
    0.54
    Activations Density 0.217%

    No Known Activations