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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11185
    Prev
    Next
    INDEX
    Explanations

    mentions of software development resources and platforms

    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
    RTSN
    -0.65
     שוליים
    -0.58
    帖最后由
    -0.53
    sterling
    -0.49
    ValueGeneration
    -0.48
    脚注の使い方
    -0.48
    __(/*!
    -0.46
    aphne
    -0.46
    OGND
    -0.46
    :✨
    -0.45
    POSITIVE LOGITS
    Linki
    0.39
    awtextra
    0.37
    تقاوى
    0.36
     ویکی‌پدیا
    0.35
    ByteBuf
    0.35
    pośred
    0.34
    ConstraintMaker
    0.34
    Erreferentziak
    0.34
     Signalez
    0.34
    nativeElement
    0.34
    Activations Density 0.886%

    No Known Activations