© 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. 24-GEMMASCOPE-RES-16K
    6. 1773
    Prev
    Next
    INDEX
    Explanations

    dates and numerical values within a specific context

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

    Appears after a year

    np_acts-logits-general · gemini-2.0-flash

    dates of establishment or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.51
     nonUne
    -0.51
    tvguidetime
    -0.50
    ciuta
    -0.50
     Процитовано
    -0.50
    écution
    -0.50
    
    
    -0.50
    SharedCtor
    -0.48
     localObject
    -0.48
    pecabe
    -0.48
    POSITIVE LOGITS
     when
    0.48
     following
    0.45
     amid
    0.40
     Савезне
    0.39
    GTCX
    0.36
     after
    0.35
     viewDidLoad
    0.35
     while
    0.34
     involving
    0.33
     soir
    0.33
    Activations Density 0.328%

    No Known Activations