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. 15-GEMMASCOPE-RES-16K
    6. 12801
    Prev
    Next
    INDEX
    Explanations

    phrases related to renovation and construction details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themſelves
    -1.22
     Monfieur
    -1.20
     myſelf
    -1.20
     Theſe
    -1.13
     ſever
    -1.09
     itſelf
    -1.08
     pleaſure
    -1.05
     himſelf
    -1.04
     ſeveral
    -1.03
     Jefus
    -1.01
    POSITIVE LOGITS
     a
    0.49
    ironically
    0.49
     per
    0.47
     reported
    0.46
     sy
    0.46
    なんと
    0.46
     an
    0.45
     undisclosed
    0.45
    Pyx
    0.45
     hidden
    0.45
    Activations Density 0.293%

    No Known Activations