© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1637
    Prev
    Next
    INDEX
    Explanations

    frequent use of the word "the" and expressions related to conditions and contexts being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FXML
    -0.66
    Panamoan
    -0.62
    NVIC
    -0.62
    EndGlobalSection
    -0.57
    eroon
    -0.56
    pict
    -0.55
    pau
    -0.55
    GEBURTSDATUM
    -0.55
    SharedCtor
    -0.54
    🇽
    -0.54
    POSITIVE LOGITS
     geométrico
    0.39
     Económica
    0.38
    pēc
    0.37
     sommige
    0.36
     ettei
    0.36
     bēr
    0.35
     istrinya
    0.35
    Parameteri
    0.35
     jueces
    0.35
     forfatter
    0.35
    Activations Density 1.158%

    No Known Activations