© 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. 10-GEMMASCOPE-RES-16K
    11. 15392
    Prev
    Next
    INDEX
    Explanations

    functions and methods typically used in programming, particularly for string and file manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mere
    -0.55
    ynh
    -0.48
     long
    -0.43
     
    -0.41
     parti
    -0.41
     bear
    -0.40
     care
    -0.40
    Mucho
    -0.40
     Kay
    -0.39
    alip
    -0.39
    POSITIVE LOGITS
    enterOuterAlt
    0.94
    NameInMap
    0.93
    Kaynakça
    0.92
     mergeFrom
    0.91
     propOrder
    0.88
    PageRoute
    0.88
     makeStyles
    0.84
     AssemblyTitle
    0.84
    UserScript
    0.84
    principalTable
    0.83
    Activations Density 0.251%

    No Known Activations