© 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. 0-GEMMASCOPE-RES-16K
    6. 10712
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to limits and convergence in a formal mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verſch
    -0.85
     Waſſer
    -0.83
     Geſch
    -0.81
    <unused79>
    -0.80
    <unused42>
    -0.79
    <unused47>
    -0.79
    <unused51>
    -0.79
    <unused16>
    -0.79
    [@BOS@]
    -0.79
    <unused3>
    -0.79
    POSITIVE LOGITS
    ^{*
    1.51
    ^{-
    1.29
    ^{+
    1.28
    ^{-}
    1.14
    }^{+
    1.14
    }^{*
    1.09
    ^{*}
    1.09
    }^{-
    1.07
    ^{*}$
    1.05
    ^{-\
    1.05
    Activations Density 0.335%

    No Known Activations