© 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 - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 3307
    Prev
    Next
    INDEX
    Explanations

    references to film production and actors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     global
    -0.72
     глоба
    -0.65
     Sheeran
    -0.53
     globally
    -0.53
    катери
    -0.52
    bandcamp
    -0.52
    global
    -0.50
     Neymar
    -0.50
     globales
    -0.50
     project
    -0.49
    POSITIVE LOGITS
    
    0.75
     Мексичка
    0.74
     mußte
    0.71
     läßt
    0.71
     wußte
    0.69
     muß
    0.69
    出版年
    0.67
    <bos>
    0.66
     <>",
    0.66
     gynnwys
    0.63
    Activations Density 0.527%

    No Known Activations