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. 10-GEMMASCOPE-RES-16K
    6. 3052
    Prev
    Next
    INDEX
    Explanations

    affirmative statements and phrases that indicate personal feelings or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -1.43
     itſelf
    -1.43
     myſelf
    -1.41
     himſelf
    -1.36
     Efq
    -1.35
     Reſ
    -1.31
     themſelves
    -1.30
     pleaſure
    -1.29
     Monfieur
    -1.26
     fubject
    -1.26
    POSITIVE LOGITS
     a
    1.06
     the
    0.97
     “
    0.87
     
    0.83
     an
    0.82
    ’
    0.73
     its
    0.72
     ‘
    0.72
    s
    0.71
     time
    0.69
    Activations Density 0.210%

    No Known Activations