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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16137
    Prev
    Next
    INDEX
    Explanations

    actions or commands related to adding or integrating items in a process, particularly in a shopping or programming context

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

    Following tokens like "to", "up", "in"

    np_acts-logits-general · gemini-2.0-flash

    add to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.38
     here
    -0.36
     nearby
    -0.34
     erop
    -0.34
    出版年
    -0.32
     ici
    -0.32
     Nearby
    -0.32
     hereto
    -0.29
    Supp
    -0.29
    Nearby
    -0.29
    POSITIVE LOGITS
     Chwiliwch
    0.80
    TypedDataSet
    0.78
     addTo
    0.69
    AddTo
    0.68
    addTo
    0.65
    添加到
    0.63
     BoxDecoration
    0.60
     removeFrom
    0.60
    放到
    0.59
     writeTo
    0.59
    Activations Density 0.418%

    No Known Activations