© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 7602
    Prev
    Next
    INDEX
    Explanations

    references to policies and policy makers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.79
    Демографія
    -0.77
    تقاوى
    -0.69
     متعلقه
    -0.64
    ]--;
    -0.62
    +#+#
    -0.56
    shire
    -0.55
     NSCoder
    -0.54
     gainera
    -0.53
     propOrder
    -0.53
    POSITIVE LOGITS
     makers
    0.91
    making
    0.89
    maker
    0.88
     formulation
    0.71
     maker
    0.69
     Formulation
    0.67
    makers
    0.66
     decisions
    0.65
    holder
    0.64
     direction
    0.63
    Activations Density 0.169%

    No Known Activations