© 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. 18-GEMMASCOPE-RES-16K
    11. 2736
    Prev
    Next
    INDEX
    Explanations

    terms related to counter-terrorism efforts and law enforcement collaboration

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

    Sharing or exchanging information/ideas

    np_acts-logits-general · gemini-2.0-flash

    sharing and exchanging information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodeAttribute
    -0.46
    dotta
    -0.44
    igshid
    -0.43
    Życiorys
    -0.41
     közel
    -0.41
    tigo
    -0.40
     déroule
    -0.40
     titul
    -0.40
     канди
    -0.39
    /**
    -0.39
    POSITIVE LOGITS
     sharing
    1.91
     exchange
    1.80
     exchanging
    1.79
    sharing
    1.77
     Sharing
    1.72
    Sharing
    1.68
     shared
    1.63
     exchanged
    1.59
    exchange
    1.59
     Exchange
    1.55
    Activations Density 0.388%

    No Known Activations