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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14750
    Prev
    Next
    INDEX
    Explanations

    terms related to user authentication and credentials in programming contexts

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

    Authentication credentials

    np_acts-logits-general · gemini-2.0-flash

    password values

    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
     initComponents
    -0.68
     queſta
    -0.64
     Exactos
    -0.64
    WebServlet
    -0.63
    httphttps
    -0.62
    errHandler
    -0.61
     JpaRepository
    -0.60
    оргаш
    -0.60
    setVerticalGroup
    -0.60
    cshtml
    -0.58
    POSITIVE LOGITS
     cred
    0.37
     login
    0.35
     nadie
    0.33
     password
    0.30
     passwords
    0.30
     tr
    0.29
     whi
    0.28
     creemos
    0.28
    Combin
    0.28
     scand
    0.28
    Activations Density 0.182%

    No Known Activations