© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1309
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and logical statements relevant to mathematical proofs

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

    reasoning or deduction

    np_acts-logits-general · gemini-2.0-flash

    we obtain / deduce / conclude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.64
    NoSuchAlgorithm
    -0.61
    !("{
    -0.57
    ",&
    -0.56
    <>
    -0.55
    UIFont
    -0.53
    ricultural
    -0.53
    sometimes
    -0.52
    WillAppear
    -0.52
    ListItemIcon
    -0.51
    POSITIVE LOGITS
     puisque
    0.60
     clearly
    0.59
    Clearly
    0.58
     Clearly
    0.58
     again
    0.58
     поскольку
    0.56
    clearly
    0.56
    tagext
    0.56
    again
    0.56
     obviously
    0.55
    Activations Density 1.964%

    No Known Activations