© 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. 3-GEMMASCOPE-RES-16K
    11. 10755
    Prev
    Next
    INDEX
    Explanations

    references to time-related concepts, particularly finite time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WEBPACK
    -0.52
     فريبيس
    -0.50
    mbggenerated
    -0.49
    ModelSerializer
    -0.47
     pros
    -0.46
    patine
    -0.46
    PROS
    -0.45
     причин
    -0.45
    Pros
    -0.44
    الدراسه
    -0.44
    POSITIVE LOGITS
    TabIndex
    0.63
     finite
    0.57
    Autoritní
    0.56
     Little
    0.54
    finite
    0.48
     depth
    0.44
    Little
    0.44
    Finite
    0.42
     Depth
    0.42
     따
    0.41
    Activations Density 0.076%

    No Known Activations