Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12881
    Prev
    Next
    INDEX
    Explanations

    instances of suggestion and influence in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.55
     parlando
    -0.50
     mourut
    -0.50
    ண்டும்
    -0.49
     recibiendo
    -0.49
    さてさて
    -0.48
     receiving
    -0.48
     gewohnt
    -0.47
     Receiving
    -0.46
     generando
    -0.46
    POSITIVE LOGITS
     take
    1.35
     go
    1.29
     keep
    1.21
     make
    1.18
     try
    1.16
     get
    1.16
     give
    1.12
     use
    1.10
     choose
    1.08
     prepare
    1.08
    Activations Density 0.683%

    No Known Activations