© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 7034
    Prev
    Next
    INDEX
    Explanations

    mathematical questions asking for the largest, smallest, closest, or other relational values among numbers

    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
    addPreferredGap
    -0.58
     Quite
    -0.56
     tiennent
    -0.56
    Ibid
    -0.54
    XmlAccessorType
    -0.54
     Ibid
    -0.52
    Quite
    -0.51
     вовсе
    -0.51
     igång
    -0.51
    tymologie
    -0.51
    POSITIVE LOGITS
     correct
    0.64
    correctly
    0.62
    MessageTagHelper
    0.62
     suitable
    0.60
     given
    0.60
     folle
    0.59
     missing
    0.59
     appropriate
    0.58
     correctly
    0.57
    RunAsync
    0.56
    Activations Density 0.662%

    No Known Activations