© 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. 4061
    Prev
    Next
    INDEX
    Explanations

    instances of counting or repetition related to mathematical concepts

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

    Occurrences or repetitions

    np_acts-logits-general · gemini-2.0-flash

    counting or multiples

    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
    IntoConstraints
    -0.61
    хьтан
    -0.57
    MLLoader
    -0.53
    новниш
    -0.52
     GenerationType
    -0.52
     informée
    -0.50
    awtextra
    -0.50
    賒
    -0.49
    Népesség
    -0.48
    exitRule
    -0.47
    POSITIVE LOGITS
     twice
    1.95
    twice
    1.71
     Twice
    1.63
     thrice
    1.58
    Twice
    1.57
     repeated
    1.56
     repeatedly
    1.50
     TWICE
    1.45
    repeated
    1.45
     mehrm
    1.44
    Activations Density 0.697%

    No Known Activations