© 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. 11309
    Prev
    Next
    INDEX
    Explanations

    references to string manipulation and output functions in programming

    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
    getDoctrine
    -0.59
    égard
    -0.57
    Παραπομπές
    -0.56
     måste
    -0.54
     Consultado
    -0.51
     lệ
    -0.50
    ValueStyle
    -0.49
    brainer
    -0.47
    fäl
    -0.47
    ılığı
    -0.47
    POSITIVE LOGITS
    AxisAlignment
    1.22
    endregion
    1.12
    )(((
    1.03
     ModelExpression
    1.02
     StringBuilder
    0.84
     pinulongan
    0.78
     Initialized
    0.77
     препратки
    0.73
    ंदीखरीदारी
    0.70
     StringBuffer
    0.69
    Activations Density 0.008%

    No Known Activations