© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7376
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to equivalence relations and structures

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

    Mathematical orderings or relations

    np_acts-logits-general · gemini-2.0-flash

    ordering and relations induced by operators

    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
    ChildScrollView
    -0.54
     régionales
    -0.45
     محفوظة
    -0.43
    
    -0.39
    зулта
    -0.38
    adaptiveStyles
    -0.38
    Styleable
    -0.37
     financière
    -0.37
     igenom
    -0.37
    styleable
    -0.36
    POSITIVE LOGITS
     induced
    0.56
     operator
    0.54
     operators
    0.49
     strongest
    0.46
    induced
    0.46
    operator
    0.44
     Induced
    0.44
     operations
    0.43
     surface
    0.43
     Operator
    0.43
    Activations Density 2.321%

    No Known Activations