© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5732
    Prev
    Next
    INDEX
    Explanations

    references to being "ahead" or forward-looking in time or context

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

    "ahead" or its translations

    np_acts-logits-general · gemini-2.0-flash

    ahead of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    Json
    -0.39
    /*
    -0.38
    CardModule
    -0.37
    Random
    -0.36
    Artigo
    -0.36
     trụ
    -0.35
     Or
    -0.35
    Plugin
    -0.34
    random
    -0.33
    //
    -0.33
    POSITIVE LOGITS
     Ahead
    1.93
     ahead
    1.90
    ahead
    1.80
    Ahead
    1.78
     AHEAD
    1.73
     adelant
    0.79
     voraus
    0.78
     abreast
    0.76
     delante
    0.75
    переди
    0.74
    Activations Density 0.200%

    No Known Activations