Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15653
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal definitions and conditions surrounding the status and rights of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatefulWidget
    -0.45
    glBegin
    -0.39
    ledo
    -0.39
    uebe
    -0.38
    definitely
    -0.38
    favourite
    -0.38
    tonsoft
    -0.38
     nahilalakip
    -0.38
    hep
    -0.37
     ***!
    -0.37
    POSITIVE LOGITS
     equivalent
    0.50
     altrimenti
    0.48
    iornamento
    0.47
    UrlResolution
    0.46
     equivalente
    0.45
     otherwise
    0.44
     noDo
    0.43
    :][
    0.42
    ConstraintLayout
    0.42
    pherals
    0.41
    Activations Density 0.517%

    No Known Activations