© 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. 5-GEMMASCOPE-RES-16K
    11. 10834
    Prev
    Next
    INDEX
    Explanations

    phrases or terms emphasizing clarity and certainty in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -1.00
    didSet
    -0.95
    solicited
    -0.90
    Collegamenti
    -0.85
    tissement
    -0.85
    IndentedString
    -0.83
    djangoproject
    -0.82
    Bibliograf
    -0.82
     @"/
    -0.81
    눠
    -0.80
    POSITIVE LOGITS
     clear
    2.06
     Clear
    1.96
    Clear
    1.90
     CLEAR
    1.87
    clear
    1.78
    CLEAR
    1.60
     clearer
    1.55
     clarity
    1.40
     clears
    1.38
     CLAR
    1.36
    Activations Density 0.055%

    No Known Activations