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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12075
    Prev
    Next
    INDEX
    Explanations

    date-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cshtml
    -0.42
    parsedMessage
    -0.40
    messageInfo
    -0.40
    קישורים
    -0.39
     विश्वसनीयता
    -0.38
    CPtr
    -0.38
    évaluateur
    -0.37
    Ligações
    -0.37
    قایناقلار
    -0.35
    iprot
    -0.34
    POSITIVE LOGITS
     year
    0.79
    Year
    0.71
     Year
    0.68
     calendar
    0.68
     month
    0.67
     dates
    0.65
    GEBURTSDATUM
    0.63
     Month
    0.62
    Month
    0.60
    Calendar
    0.60
    Activations Density 0.188%

    No Known Activations