© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5231
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting used in text, including punctuation and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Characters within brackets: [], {}, or ()

    np_acts-logits-general · gemini-2.0-flash

    code and bracketed symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.61
     CreateTagHelper
    -0.59
     feroit
    -0.49
     CYTHON
    -0.48
     pouvoit
    -0.46
     समीक्षाओं
    -0.46
     bezeichneter
    -0.45
     noDo
    -0.45
    pecabe
    -0.43
    Portály
    -0.43
    POSITIVE LOGITS
    ‚¬
    0.54
    $)$
    0.54
    ">)</
    0.53
    <>();
    0.52
    |()
    0.50
    CppCodeGen
    0.50
    %)$
    0.49
    //{
    0.49
    bigr
    0.47
    [toxicity=0]
    0.47
    Activations Density 0.838%

    No Known Activations