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. 20-GEMMASCOPE-RES-16K
    6. 1084
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to trials and sentences

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

    "For" preceding an accusation or justification

    np_acts-logits-general · gemini-2.0-flash

    for *[reason/justification]*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     fieldNum
    -0.43
    ⓧ
    -0.38
     oprot
    -0.37
    WithIOException
    -0.35
    TypedDataSet
    -0.35
    dessert
    -0.32
    MethodManager
    -0.32
     lámpara
    -0.32
     alive
    -0.32
     bâ
    -0.32
    POSITIVE LOGITS
     kasarigan
    0.63
    URLException
    0.57
    AnchorStyles
    0.57
    Parcelize
    0.52
    genodigd
    0.50
     unicórnio
    0.48
    ftagPool
    0.47
    prete
    0.46
     typelib
    0.46
     mangel
    0.45
    Activations Density 0.417%

    No Known Activations