© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 9903
    Prev
    Next
    INDEX
    Explanations

    syntactic elements related to functions and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.59
    esModule
    -0.57
     Comprometido
    -0.55
     defaultstate
    -0.54
    bootstrapcdn
    -0.54
    ArrowToggle
    -0.52
    GOTREF
    -0.52
    AndEndTag
    -0.51
    principalColumn
    -0.51
    évaluateur
    -0.47
    POSITIVE LOGITS
     x
    1.52
     X
    1.38
    x
    1.21
    X
    1.17
    getX
    1.01
     getX
    0.90
    GetX
    0.86
    𝑥
    0.86
    ｘ
    0.85
     х
    0.84
    Activations Density 1.216%

    No Known Activations