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. 15946
    Prev
    Next
    INDEX
    Explanations

    phrases related to digital security and online privacy

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

    Following a period or punctuation mark

    np_acts-logits-general · gemini-2.0-flash
    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
    MemoryWarning
    -0.66
    BeginInit
    -0.59
    UnusedPrivate
    -0.56
    \{\\
    -0.56
    principalTable
    -0.54
    XmlAccessType
    -0.54
    setupUi
    -0.54
     InputDecoration
    -0.54
     estekak
    -0.52
     StatelessWidget
    -0.52
    POSITIVE LOGITS
    Nuorodos
    0.47
     Roskov
    0.43
    InjectAttribute
    0.41
    uxxxx
    0.40
     հղումներ
    0.40
     Italijani
    0.39
     podjela
    0.38
     Wiktionnaire
    0.38
    ésultat
    0.37
    Спасылкі
    0.36
    Activations Density 1.058%

    No Known Activations