© 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 EvalsExportsinterp-engineNEWAPI 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. 12244
    Prev
    Next
    INDEX
    Explanations

    curly braces and other punctuation, indicating structure in programming code

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

    Code within curly brackets

    np_acts-logits-general · gemini-2.0-flash

    code snippets

    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
     Efq
    -1.02
     myſelf
    -0.94
     Monfieur
    -0.91
     ſhe
    -0.88
     whoſe
    -0.87
     ſtand
    -0.86
     Theſe
    -0.83
     ſeveral
    -0.83
     becauſe
    -0.82
     Daß
    -0.82
    POSITIVE LOGITS
     —
    0.46
     --
    0.40
     
    0.39
     pré
    0.37
    #:
    0.37
     vai
    0.36
     premium
    0.36
     pere
    0.36
     dila
    0.36
    up
    0.35
    Activations Density 0.126%

    No Known Activations