© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 8833
    Prev
    Next
    INDEX
    Explanations

    symbolic representations and notations used in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.61
     للمعارف
    -0.60
    évaluateur
    -0.51
     propOrder
    -0.51
    GEBURTSDATUM
    -0.50
     GenerationType
    -0.49
     ―――――
    -0.49
     שוליים
    -0.48
    PerformLayout
    -0.48
    +#+#
    -0.48
    POSITIVE LOGITS
    AddTagHelper
    0.38
    LEADING
    0.37
    telse
    0.36
    Jereo
    0.36
     Anges
    0.36
    alea
    0.35
    будь
    0.35
     Italijanski
    0.34
    ApiModelProperty
    0.34
     Nieren
    0.34
    Activations Density 0.995%

    No Known Activations