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. 2767
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate processes or requirements

    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
     pleaſure
    -1.44
     Jefus
    -1.38
     Monfieur
    -1.32
     Majefty
    -1.27
     faſt
    -1.25
     themſelves
    -1.24
     Diſ
    -1.24
     myſelf
    -1.23
     houſe
    -1.23
     Efq
    -1.21
    POSITIVE LOGITS
     inorder
    1.10
     afin
    1.01
     Afin
    0.84
    Afin
    0.82
     чтобы
    0.82
     أجل
    0.77
     aby
    0.75
     כדי
    0.74
    inorder
    0.74
     order
    0.74
    Activations Density 0.069%

    No Known Activations