© 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. 1-GEMMASCOPE-RES-16K
    11. 3344
    Prev
    Next
    INDEX
    Explanations

    terms related to direct action or direct processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.77
     Verſ
    -0.68
     Geſ
    -0.67
     betweenstory
    -0.67
     resourceCulture
    -0.65
     Monfieur
    -0.63
    <?
    -0.63
     Perſ
    -0.62
     pleaſure
    -0.62
     BorderSide
    -0.60
    POSITIVE LOGITS
     direct
    1.13
    direct
    1.08
     later
    1.05
    Direct
    1.04
     Direct
    1.02
    later
    1.01
    Later
    0.88
     indirect
    0.86
    indirect
    0.83
     Later
    0.82
    Activations Density 0.178%

    No Known Activations