Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10945
    Prev
    Next
    INDEX
    Explanations

    phrases related to balance or duality in situations or concepts

    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
     Monfieur
    -0.94
     feroit
    -0.90
     auroit
    -0.86
     Efq
    -0.85
    .*")]
    -0.84
     étoient
    -0.84
     étoit
    -0.81
     pleaſure
    -0.81
     pouvoit
    -0.79
     avoient
    -0.78
    POSITIVE LOGITS
    RectangleBorder
    0.70
     also
    0.61
     andererseits
    0.60
    我又
    0.56
    atellite
    0.56
    又能
    0.56
     gleichzeitig
    0.51
    但也
    0.51
     Also
    0.50
    一方で
    0.50
    Activations Density 0.199%

    No Known Activations