© 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. 33-GEMMASCOPE-RES-16K
    6. 10979
    Prev
    Next
    INDEX
    Explanations

    references to the Java programming language and its libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.46
    HttpPost
    -0.45
     faro
    -0.42
     pun
    -0.41
     brou
    -0.41
     CI
    -0.40
    BeginContext
    -0.40
    коменду
    -0.40
    новниш
    -0.40
    InputBorder
    -0.40
    POSITIVE LOGITS
    util
    0.81
    math
    0.63
    io
    0.60
    awt
    0.60
    lang
    0.54
     anún
    0.54
     delegación
    0.52
    nio
    0.50
     bolsillo
    0.50
    time
    0.49
    Activations Density 0.028%

    No Known Activations