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. 21-GEMMASCOPE-RES-16K
    6. 8437
    Prev
    Next
    INDEX
    Explanations

    property accessors, specifically 'get' methods within code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]:
    
    -0.46
    nt
    -0.45
    taus
    -0.43
    httphttps
    -0.43
    jako
    -0.43
    !("{}",
    -0.42
    ступ
    -0.41
    gré
    -0.39
     @"
    -0.39
    so
    -0.39
    POSITIVE LOGITS
     ModelExpression
    0.84
     resourceCulture
    0.78
    ंदीखरीदारी
    0.74
    queryInterface
    0.72
     defaultstate
    0.72
    complexType
    0.68
    SerializedSize
    0.68
    complexContent
    0.67
    Nuorodos
    0.65
    readFileSync
    0.64
    Activations Density 0.022%

    No Known Activations