© 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. 15-GEMMASCOPE-RES-16K
    11. 1740
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation used in coding or scripting languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
    ValueStyle
    -0.59
     gyhoeddwyd
    -0.58
     autorytatywna
    -0.57
     betweenstory
    -0.56
    hyrchwyd
    -0.56
    GOTREF
    -0.56
     يتيمه
    -0.55
    AutoScaleMode
    -0.54
    AndroidJUnit
    -0.53
    الحياه
    -0.52
    POSITIVE LOGITS
    (&:
    0.58
    ->
    0.52
    ()->
    0.50
    ]->
    0.47
     own
    0.46
    所
    0.45
    <>("
    0.44
    :].
    0.44
    setObjectName
    0.43
    ']->
    0.43
    Activations Density 0.223%

    No Known Activations