© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7550
    Prev
    Next
    INDEX
    Explanations

    names or titles with the suffix "ji"

    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
    хьтан
    -0.56
    UrlResolution
    -0.54
    MessageOf
    -0.49
    EndInit
    -0.47
     дописавши
    -0.47
    oa̍t
    -0.46
    #+#
    -0.44
    raborty
    -0.44
    ChildScrollView
    -0.43
     geladeira
    -0.42
    POSITIVE LOGITS
     Stanley
    0.79
    ji
    0.74
    Stanley
    0.71
     Ji
    0.69
     Stat
    0.67
     ji
    0.63
     Stan
    0.63
     stat
    0.61
    Ji
    0.61
     STANLEY
    0.60
    Activations Density 0.656%

    No Known Activations