© 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. 38-GEMMASCOPE-RES-16K
    11. 7637
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and concepts related to rights and government policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    U
    -1.59
     U
    -1.53
    u
    -1.44
     u
    -1.36
    ú
    -0.94
    Ｕ
    -0.91
    У
    -0.89
    у
    -0.85
    ù
    -0.84
    ｕ
    -0.82
    POSITIVE LOGITS
     invokingState
    0.50
    المناصب
    0.49
    esez
    0.43
     Италијани
    0.42
    devamını
    0.42
    yntaxException
    0.42
    ctivos
    0.41
     SwitchCompat
    0.39
    berdayakan
    0.38
    marginHorizontal
    0.38
    Activations Density 1.725%

    No Known Activations