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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 15595
    Prev
    Next
    INDEX
    Explanations

    references or mentions of birthdates and categories related to people

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

    "(born" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    birth dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.78
     smtplib
    -0.59
    ыргыз
    -0.58
    BufferException
    -0.57
     iNdEx
    -0.56
    argout
    -0.55
    rrggbb
    -0.52
    Билгалдахарш
    -0.52
     HttpHeaders
    -0.52
    السكان
    -0.52
    POSITIVE LOGITS
     born
    1.24
     Born
    1.12
    Born
    1.12
    born
    1.11
     birth
    1.06
     BORN
    0.99
    BORN
    0.97
    birth
    0.94
     Birth
    0.90
    lahir
    0.85
    Activations Density 0.158%

    No Known Activations