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. 8-GEMMASCOPE-RES-16K
    6. 11260
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases indicating choices and alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toBeDefined
    -0.66
    PerformLayout
    -0.65
    cinnati
    -0.62
     Perci
    -0.57
     ролях
    -0.53
    AppendLine
    -0.53
    namely
    -0.51
     außerdem
    -0.51
    ละ
    -0.49
    ново
    -0.49
    POSITIVE LOGITS
     whatever
    0.86
    不论
    0.85
    hichever
    0.80
     apapun
    0.80
    Whatever
    0.78
     whichever
    0.78
     regardless
    0.77
     whether
    0.76
    不管
    0.76
    无论
    0.76
    Activations Density 0.273%

    No Known Activations