© 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. 15-GEMMASCOPE-RES-16K
    11. 2567
    Prev
    Next
    INDEX
    Explanations

    interrogative and conditional phrases related to actions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    在他
    -0.57
     Wanderers
    -0.56
     Schengen
    -0.55
    chtenstein
    -0.52
    sätzlich
    -0.51
     Soccerway
    -0.51
    פשר
    -0.50
     nguyen
    -0.49
    因为他
    -0.49
    ollectionView
    -0.49
    POSITIVE LOGITS
     it
    0.89
     the
    0.77
     they
    0.68
     those
    0.66
     anyone
    0.65
     you
    0.64
    ScopeManager
    0.64
    providedIn
    0.64
     actualité
    0.63
     we
    0.63
    Activations Density 0.115%

    No Known Activations