Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 8705
    Prev
    Next
    INDEX
    Explanations

    references to types or structures of forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]);
    
    -0.84
    AJAS
    -0.83
    "])
    
    -0.83
     Keegan
    -0.83
     Laredo
    -0.78
     Cáceres
    -0.77
     Bracken
    -0.77
     Leal
    -0.76
     NCC
    -0.76
    ()]
    
    -0.76
    POSITIVE LOGITS
     FORM
    1.74
     Form
    1.60
     Forms
    1.56
    form
    1.52
    Form
    1.51
     form
    1.50
    FORM
    1.49
     forms
    1.49
     FORMS
    1.49
    forms
    1.41
    Activations Density 0.098%

    No Known Activations