Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12120
    Prev
    Next
    INDEX
    Explanations

    references to small size or small quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.83
    enumi
    -0.69
    uvo
    -0.64
    +#+
    -0.62
    FileChooser
    -0.60
     Dinosaurs
    -0.60
    ectoria
    -0.59
    Награды
    -0.58
    PYX
    -0.57
    Hozzáférés
    -0.57
    POSITIVE LOGITS
     small
    3.22
    Small
    3.04
     Small
    3.04
    small
    3.01
     SMALL
    2.87
    SMALL
    2.69
     tiny
    2.20
     kleine
    2.10
     kleinen
    2.07
     smal
    2.04
    Activations Density 0.093%

    No Known Activations