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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 9936
    Prev
    Next
    INDEX
    Explanations

    references to the dot notation or related 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
    ThroughAttribute
    -0.48
    StructEnd
    -0.46
     doInBackground
    -0.46
    搞
    -0.45
     فريبيس
    -0.45
    apsed
    -0.44
    ishments
    -0.42
    ansas
    -0.42
    Shirt
    -0.41
    তথ্যসূত্র
    -0.40
    POSITIVE LOGITS
     Dot
    1.10
     dot
    1.00
    Dot
    0.95
     tap
    0.94
    dot
    0.94
     Tap
    0.88
    Tap
    0.79
     dots
    0.78
     DOT
    0.71
    tap
    0.69
    Activations Density 0.130%

    No Known Activations