© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14703
    Prev
    Next
    INDEX
    Explanations

    keywords related to duties and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     both
    -0.39
     however
    -0.35
     certain
    -0.31
     Bahía
    -0.30
     зато
    -0.29
     universel
    -0.28
     Bekasi
    -0.27
     four
    -0.27
    tså
    -0.26
    ņš
    -0.26
    POSITIVE LOGITS
    __((
    0.69
    RegressionTest
    0.68
     ExecuteAsync
    0.67
    writeField
    0.65
     ModelExpression
    0.63
    tagPool
    0.63
    Autoritní
    0.61
    Personendaten
    0.61
    ſelben
    0.61
     getSystem
    0.60
    Activations Density 1.472%

    No Known Activations