© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8899
    Prev
    Next
    INDEX
    Explanations

    concepts related to boundaries and separations between different entities or ideas

    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
    Others
    -0.69
     Others
    -0.66
    others
    -0.62
    jątk
    -0.60
     otro
    -0.58
    otts
    -0.56
     Otros
    -0.55
     supplémentaires
    -0.54
     restTemplate
    -0.53
    ymce
    -0.52
    POSITIVE LOGITS
     sexes
    1.09
     different
    1.04
     disparate
    0.98
     genders
    0.91
     generations
    0.87
     hemispheres
    0.85
     dissimilar
    0.81
    different
    0.81
     incompatible
    0.79
     opposing
    0.79
    Activations Density 0.468%

    No Known Activations