© 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. 12348
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and certain function calls

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

    Mathematical symbols: +, -, →, [, ], $, etc

    np_acts-logits-general · gemini-2.0-flash

    addition and plus signs

    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
    HtmlAttribute
    -0.68
     middle
    -0.46
    abil
    -0.43
     Mit
    -0.43
     ganzen
    -0.41
    Eri
    -0.41
    ansk
    -0.41
    </
    -0.41
    Mit
    -0.40
    diz
    -0.40
    POSITIVE LOGITS
     плюс
    1.25
     plus
    1.21
     + 
    1.16
     PLUS
    1.14
    ₂+
    1.13
     $+$
    1.10
     +
    1.06
    $+$
    1.04
    plus
    1.04
     ditambah
    1.04
    Activations Density 1.061%

    No Known Activations