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. 16-GEMMASCOPE-RES-16K
    6. 12017
    Prev
    Next
    INDEX
    Explanations

    terms associated with password management and security protocols

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

    Text near password-related words

    np_acts-logits-general · gemini-2.0-flash

    password and otp codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nskap
    -0.57
    IBOutlet
    -0.57
    JScrollPane
    -0.54
     Citation
    -0.50
     ordenar
    -0.48
     kauf
    -0.48
     unloading
    -0.47
    pino
    -0.47
     unload
    -0.45
     Qualitäts
    -0.45
    POSITIVE LOGITS
     免
    0.61
     @"/
    0.59
     &___
    0.58
    ]-'
    0.58
    TestingModule
    0.56
     kaarangay
    0.55
     Pote
    0.55
     lockout
    0.55
    Clik
    0.55
    VYMaps
    0.54
    Activations Density 0.201%

    No Known Activations