© 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. 39562
    Prev
    Next
    INDEX
    Explanations

    terms related to licensing and permissions

    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
     Efq
    -0.65
    CppCodeGen
    -0.60
     Monfieur
    -0.59
     Administrativna
    -0.55
    +#+#
    -0.52
     fometimes
    -0.51
    奈川
    -0.51
     juſ
    -0.51
     Theſe
    -0.51
     woe
    -0.49
    POSITIVE LOGITS
    MemoryWarning
    0.80
    expandindo
    0.77
    ">//
    0.76
    Bibliograf
    0.74
    __':
    
    0.71
    serviceWorker
    0.71
     Référence
    0.70
     AssemblyCulture
    0.68
    hibli
    0.65
     дописавши
    0.64
    Activations Density 0.001%

    No Known Activations