© 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. 7-GEMMASCOPE-RES-16K
    11. 14902
    Prev
    Next
    INDEX
    Explanations

    references to the data type "string" in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Toul
    -0.94
     gdyby
    -0.83
    ึกษา
    -0.82
    roxene
    -0.82
    setDo
    -0.82
     متعلقه
    -0.79
    rachtet
    -0.78
    solete
    -0.78
     ويكيپيديا
    -0.77
    onus
    -0.77
    POSITIVE LOGITS
    string
    1.10
    er
    1.00
     string
    0.99
    ling
    0.93
    ly
    0.92
     fio
    0.81
    ster
    0.81
    y
    0.80
     Greif
    0.75
    ([]
    0.74
    Activations Density 0.092%

    No Known Activations