© 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. 28-GEMMASCOPE-RES-16K
    6. 4536
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to quantum mechanics and statistical estimation

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

    preceding mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    imperfectly or incompletely described

    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
     Paglinawan
    -0.69
     pinulongan
    -0.65
    RenderAtEndOf
    -0.58
    AddTagHelper
    -0.57
     undamaged
    -0.56
    AndEndTag
    -0.55
     unharmed
    -0.55
     Infórmanos
    -0.54
     kaarangay
    -0.54
     unaffected
    -0.54
    POSITIVE LOGITS
     imperfect
    1.01
     incomplete
    0.91
     imperfectly
    0.77
     Incomplete
    0.75
    incomplete
    0.75
     deviate
    0.71
     imperfection
    0.66
     imperf
    0.65
    Incomplete
    0.64
     inaccurate
    0.63
    Activations Density 1.280%

    No Known Activations