© 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. 28-GEMMASCOPE-RES-16K
    11. 6502
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation relevant to probability and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Less than

    np_acts-logits-general · gemini-2.0-flash

    infinite values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.46
    HandlerContext
    -0.39
     يتيمه
    -0.38
     ENC
    -0.37
    LayoutStyle
    -0.36
     arşivlendi
    -0.35
     Magdalen
    -0.34
    TabLayout
    -0.34
     OJ
    -0.34
     CreateTagHelper
    -0.34
    POSITIVE LOGITS
     infinite
    1.28
     infinity
    1.21
    infinite
    1.07
    infinity
    1.05
    Infinite
    1.05
     unlimited
    1.03
     Infinite
    1.03
     infinito
    1.02
     Infinity
    1.01
    無限
    1.01
    Activations Density 0.854%

    No Known Activations