© 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. 2-GEMMASCOPE-RES-16K
    6. 7415
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.78
     ModelExpression
    -0.71
     MediatR
    -0.60
    StoryboardSegue
    -0.58
     nadzieję
    -0.54
     EconPapers
    -0.54
     solito
    -0.52
     Kwon
    -0.52
     unknownFields
    -0.52
    SDAY
    -0.51
    POSITIVE LOGITS
     Himo
    0.63
     @"
    0.61
     pin
    0.59
    tigheter
    0.59
    </blockquote>
    0.56
    $",
    0.56
    Mach
    0.56
    کتر
    0.56
    ."\
    0.56
    gelijk
    0.56
    Activations Density 0.361%

    No Known Activations