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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7536
    Prev
    Next
    INDEX
    Explanations

    repetitive patterns in the text, particularly the term "rec" and variations related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pulseira
    -0.60
    attutto
    -0.51
     miró
    -0.50
     cérebro
    -0.50
     sogni
    -0.50
    cartão
    -0.50
     renfor
    -0.49
     móvel
    -0.49
     plomb
    -0.48
     secundario
    -0.48
    POSITIVE LOGITS
    rec
    0.82
     rec
    0.81
    GEBURTSDATUM
    0.76
     disambiguazione
    0.60
     Rec
    0.58
    ValueStyle
    0.56
     recruited
    0.52
    Rec
    0.51
    DIPSETTING
    0.50
     bezeichneter
    0.49
    Activations Density 0.195%

    No Known Activations