© 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. 2-GEMMASCOPE-RES-16K
    6. 4141
    Prev
    Next
    INDEX
    Explanations

    characters and special symbols often associated with computer code or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ilustracja
    -0.46
    enumi
    -0.45
     zijne
    -0.41
     miniaturka
    -0.41
     plufieurs
    -0.40
    ญิง
    -0.40
     dezelve
    -0.38
    berdayakan
    -0.38
    ooplankton
    -0.37
     anzunehmen
    -0.37
    POSITIVE LOGITS
     }{@
    0.63
    nloa
    0.56
     nakalista
    0.54
    AndEndTag
    0.52
    :✨
    0.52
     disambiguazione
    0.52
    <bos>
    0.49
    Tikang
    0.48
    tahui
    0.48
    astéroïdes
    0.47
    Activations Density 3.523%

    No Known Activations