© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3026
    Prev
    Next
    INDEX
    Explanations

    code structures that include function definitions and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.56
    __).
    -0.55
    pyplot
    -0.53
     ioe
    -0.52
    oredCriteria
    -0.50
    StoryboardSegue
    -0.49
     متعلقه
    -0.48
    (")");
    -0.48
    AutoField
    -0.47
    phide
    -0.46
    POSITIVE LOGITS
    ñera
    0.60
    ibatis
    0.56
    stateProvider
    0.54
    saco
    0.51
    yship
    0.50
    beros
    0.49
    beispiel
    0.49
    ipedi
    0.49
    Smarty
    0.49
    ::::::::
    0.48
    Activations Density 0.588%

    No Known Activations