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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 11735
    Prev
    Next
    INDEX
    Explanations

    structures and operations involving class methods and properties in an object-oriented programming context

    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
     Roskov
    -0.77
    featureID
    -0.72
    RegistryLite
    -0.68
    +#+#
    -0.64
     newOwner
    -0.61
    WarningLevel
    -0.59
    windowFixed
    -0.57
    futbolista
    -0.56
    InputTagHelper
    -0.56
     AttributeSet
    -0.55
    POSITIVE LOGITS
     "..\..\..\
    0.54
     "..\..\
    0.53
    ه‌اند
    0.50
    fai
    0.50
     continúas
    0.49
    bigsqcup
    0.49
    Spec
    0.49
     Juliette
    0.49
     Pata
    0.48
    /**
    0.48
    Activations Density 0.154%

    No Known Activations