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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13900
    Prev
    Next
    INDEX
    Explanations

    terms related to loans and betting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toggler
    -0.79
     Heid
    -0.75
    delaire
    -0.74
    DateTimeField
    -0.74
    sns
    -0.72
    uxxxx
    -0.72
    databind
    -0.71
     Lys
    -0.70
    titleLabel
    -0.70
    autoconfigure
    -0.70
    POSITIVE LOGITS
    Portale
    1.00
     Betts
    0.95
     Kaye
    0.94
     noDo
    0.93
     везе
    0.85
     bParam
    0.85
     Tobi
    0.84
     Sarm
    0.81
     loans
    0.80
     Borrow
    0.78
    Activations Density 0.441%

    No Known Activations