© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56349
    Prev
    Next
    INDEX
    Explanations

    method calls and object property access in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exitRule
    -0.52
    IndentedString
    -0.48
    neden
    -0.47
     Accesat
    -0.46
     transfieras
    -0.46
     питания
    -0.42
     traverses
    -0.42
     Universite
    -0.42
     covers
    -0.41
    äksi
    -0.41
    POSITIVE LOGITS
    حياتها
    0.77
     Italijani
    0.66
    favourable
    0.65
    AnchorTagHelper
    0.64
     springfox
    0.64
    weile
    0.62
     кӀ
    0.61
    UnsafeEnabled
    0.61
     défa
    0.60
    __':
    
    0.59
    Activations Density 0.018%

    No Known Activations