© 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. 56340
    Prev
    Next
    INDEX
    Explanations

    references to academic citations or studies

    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
    SBATCH
    -0.79
     الحره
    -0.72
     cdti
    -0.69
     Picchu
    -0.68
    Karakteristik
    -0.64
    ChildIndex
    -0.64
    WebpackPlugin
    -0.63
     AssemblyVersion
    -0.61
     isInitialized
    -0.61
    calyptic
    -0.59
    POSITIVE LOGITS
    štu
    0.52
    HasAnnotation
    0.51
     hoort
    0.50
     Cronin
    0.49
    #+#
    0.48
     ниже
    0.48
     verbund
    0.48
     تعدى
    0.48
    :+:
    0.45
     eind
    0.45
    Activations Density 0.015%

    No Known Activations