© 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. 3-GEMMASCOPE-RES-16K
    11. 15951
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions around the theme of creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?}",
    -0.61
    endphp
    -0.60
     nobile
    -0.58
     afge
    -0.58
    endpush
    -0.57
     μην
    -0.57
    interceptors
    -0.56
    вић
    -0.56
    bbene
    -0.55
    %;
    -0.55
    POSITIVE LOGITS
     creation
    2.92
     Creation
    2.77
    Creation
    2.56
    creation
    2.49
     creations
    2.36
     creator
    1.99
     création
    1.97
     creación
    1.93
     Creations
    1.92
     creators
    1.88
    Activations Density 0.100%

    No Known Activations