© 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. 5-GEMMASCOPE-RES-16K
    11. 13729
    Prev
    Next
    INDEX
    Explanations

    function and method calls related to object manipulation and data structure operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.60
    \{\\
    -0.60
    HomeAsUp
    -0.50
    Dr
    -0.49
     infatti
    -0.47
    HomeAsUpEnabled
    -0.47
    URIComponent
    -0.47
    сні
    -0.44
    inn
    -0.44
     disambiguazione
    -0.43
    POSITIVE LOGITS
    ]--;
    0.90
    Autoritní
    0.67
     ITIS
    0.62
      (
    0.61
     محفوظة
    0.60
    Discografia
    0.60
     createState
    0.59
     ComVisible
    0.58
    usermodel
    0.57
    wieś
    0.57
    Activations Density 0.458%

    No Known Activations