© 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. 3717
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or emphasis

    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
    جغرافيا
    -0.77
    exels
    -0.55
    BindingResult
    -0.54
    bedingt
    -0.49
    ביוגרפיה
    -0.48
    évaluateur
    -0.48
    あく
    -0.48
    DockStyle
    -0.48
     internetowa
    -0.48
    ide
    -0.48
    POSITIVE LOGITS
     curious
    1.20
     interesting
    1.15
     odd
    1.09
     strange
    1.01
     puzzling
    0.99
     intriguing
    0.99
     surprising
    0.98
     fascinating
    0.96
     disturbing
    0.95
     remarkable
    0.94
    Activations Density 0.450%

    No Known Activations