© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3586
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and logical propositions indicating requirements or recommendations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens preceding "one" and "One"

    np_acts-logits-general · gemini-2.0-flash

    completeness, full, 100%

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mbic
    -0.33
     argc
    -0.28
    cador
    -0.28
    openqa
    -0.27
     afar
    -0.27
    imageio
    -0.27
    Medium
    -0.26
    Relative
    -0.26
    jface
    -0.26
    IBE
    -0.26
    POSITIVE LOGITS
     full
    1.59
     fully
    1.55
     FULL
    1.49
     volledige
    1.38
     complete
    1.35
    全
    1.33
     Fully
    1.33
     completely
    1.30
     Full
    1.30
     completo
    1.27
    Activations Density 1.078%

    No Known Activations