© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 14468
    Prev
    Next
    INDEX
    Explanations

    patterns of notation typically used in programming or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...</
    -0.65
     and
    -0.56
     both
    -0.55
    </em>
    -0.55
     etc
    -0.54
    </s>
    -0.53
    ....
    -0.53
     once
    -0.53
    ...
    -0.53
    </h6>
    -0.52
    POSITIVE LOGITS
    7
    0.63
    5
    0.62
    6
    0.62
    4
    0.61
    9
    0.60
    8
    0.60
    1
    0.60
    3
    0.57
     utafitiHapana
    0.56
    хьтан
    0.55
    Activations Density 0.054%

    No Known Activations