© 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. 3-GEMMASCOPE-RES-16K
    11. 8566
    Prev
    Next
    INDEX
    Explanations

    repeated sequences of '6' and '9' which may indicate a specific pattern or threshold in the data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Probl
    -0.49
    Radius
    -0.47
     nonUne
    -0.46
    checkNotNull
    -0.44
     Conc
    -0.44
    comb
    -0.43
    Besch
    -0.43
     canst
    -0.43
    sense
    -0.43
     Frost
    -0.43
    POSITIVE LOGITS
     EconPapers
    0.56
     للاسماء
    0.54
    awaiter
    0.47
     Sixteen
    0.46
     citoy
    0.42
    XVII
    0.42
    بوابة
    0.41
     sixteen
    0.41
     AssemblyTitle
    0.41
     xvii
    0.40
    Activations Density 0.242%

    No Known Activations