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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 13089
    Prev
    Next
    INDEX
    Explanations

    components related to programming attributes and metadata handling in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.63
     Cramer
    -0.59
     Albanian
    -0.56
     Graham
    -0.56
     Crusaders
    -0.55
    Bissau
    -0.55
     Albania
    -0.55
     Shanks
    -0.54
     Alban
    -0.54
     BSP
    -0.54
    POSITIVE LOGITS
     Attribute
    2.46
     attribute
    2.44
    Attribute
    2.33
     attributes
    2.22
     attr
    2.21
    attribute
    2.19
     Attributes
    2.19
    attr
    2.08
     Att
    2.06
    Attr
    2.04
    Activations Density 0.961%

    No Known Activations