© 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. 314
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is" and its variations in order to identify statements of fact or assertions

    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
     autorytatywna
    -0.64
    GEBURTSDATUM
    -0.64
    Diwedd
    -0.61
     <<<<<<<<<<<<<<
    -0.60
    μαστε
    -0.56
     unknownFields
    -0.55
     τό
    -0.52
    rovnik
    -0.52
    ViewImports
    -0.52
    belongsTo
    -0.51
    POSITIVE LOGITS
    ⓘ
    0.62
     gäller
    0.58
     half
    0.56
     tops
    0.56
     priority
    0.55
     doInBackground
    0.53
     numberOfRows
    0.52
     par
    0.50
    MemoryWarning
    0.49
     foremost
    0.48
    Activations Density 0.271%

    No Known Activations