© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 12783
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "Hello World" and related example snippets in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.49
     blevet
    -0.44
     internationaux
    -0.43
    Descripció
    -0.42
    itteet
    -0.42
    likle
    -0.41
     Wurzeln
    -0.41
    devším
    -0.41
     vannak
    -0.40
    essere
    -0.40
    POSITIVE LOGITS
     Sample
    0.95
     Example
    0.86
    Sample
    0.86
     EXAMPLE
    0.86
     sample
    0.86
     example
    0.85
    出版年
    0.84
    EXAMPLE
    0.83
    Example
    0.81
     SAMPLE
    0.81
    Activations Density 1.120%

    No Known Activations