Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 6337
    Prev
    Next
    INDEX
    Explanations

    monetary values and related mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acrylique
    -0.75
     houſe
    -0.66
     wektor
    -0.62
     avoient
    -0.61
    devamını
    -0.60
     religieux
    -0.59
     relatifs
    -0.59
     quæ
    -0.59
     colonnes
    -0.59
     feroit
    -0.58
    POSITIVE LOGITS
    RectangleBorder
    0.69
     typelib
    0.56
    ->$
    0.53
    }$}
    0.53
     }}$}
    0.52
    bitField
    0.52
    abetes
    0.51
     '{@
    0.51
     unknownFields
    0.51
     jLabel
    0.50
    Activations Density 0.019%

    No Known Activations