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

    Neuronpedia

    APICircuit 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. 25-GEMMASCOPE-RES-16K
    6. 5917
    Prev
    Next
    INDEX
    Explanations

    references to historical conflicts and territorial changes

    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
     الرياضيه
    -0.69
     opérateur
    -0.50
    copg
    -0.45
    farwyddwr
    -0.45
     académica
    -0.45
     AttributeSet
    -0.44
     LoggerFactory
    -0.44
    XmlAccessorType
    -0.44
    InputChange
    -0.44
     drip
    -0.43
    POSITIVE LOGITS
     defeated
    0.77
     armies
    0.75
     conquest
    0.74
     conquer
    0.74
     raids
    0.74
     army
    0.73
     allies
    0.73
     raiding
    0.73
     defeat
    0.72
     allied
    0.72
    Activations Density 0.703%

    No Known Activations