© 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. 10-GEMMASCOPE-RES-16K
    11. 1814
    Prev
    Next
    INDEX
    Explanations

    discussions related to specific conditions or probabilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.67
     ooit
    -0.53
    اضر
    -0.50
    kolwiek
    -0.50
    ForTesting
    -0.49
    Capítulo
    -0.49
     Pillar
    -0.49
    eful
    -0.48
    Rptr
    -0.48
     chi̍t
    -0.48
    POSITIVE LOGITS
    PerformLayout
    0.70
     certain
    0.67
     specific
    0.66
     bestimmte
    0.62
     Certain
    0.60
     تانيه
    0.58
    certain
    0.56
    specific
    0.55
    Certain
    0.55
     particular
    0.54
    Activations Density 0.494%

    No Known Activations