© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7969
    Prev
    Next
    INDEX
    Explanations

    specific characters and symbols related to data structure syntax and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ninguém
    -0.44
     simply
    -0.43
     also
    -0.40
     indeed
    -0.40
     along
    -0.39
    simply
    -0.38
     fasse
    -0.38
     now
    -0.38
     meille
    -0.38
     always
    -0.38
    POSITIVE LOGITS
    PyExc
    0.84
    $_['
    0.77
    OGND
    0.76
    ::_('
    0.73
     мәкал
    0.73
     &___
    0.72
     IActionResult
    0.72
     nakalista
    0.71
    ->___
    0.70
    ](#
    0.69
    Activations Density 0.239%

    No Known Activations