© 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. 28-GEMMASCOPE-RES-16K
    11. 4561
    Prev
    Next
    INDEX
    Explanations

    elements related to a graphical user interface (GUI) framework or components

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

    academic averages and grades

    np_acts-logits-general · gemini-2.0-flash

    average grades

    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
    Amenities
    -0.49
    transQ
    -0.42
     المرجع
    -0.39
     nests
    -0.39
    Exer
    -0.39
    Beck
    -0.38
    lankton
    -0.38
     invokingState
    -0.38
     decks
    -0.37
    ercicio
    -0.37
    POSITIVE LOGITS
     average
    0.73
     Average
    0.66
    成績
    0.63
     promedio
    0.62
     GPA
    0.61
    Average
    0.60
     AVERAGE
    0.60
     grades
    0.59
    GPA
    0.58
     averages
    0.57
    Activations Density 0.164%

    No Known Activations