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. 3-GEMMASCOPE-RES-16K
    6. 10085
    Prev
    Next
    INDEX
    Explanations

    references to content-related elements in programming or markup languages

    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
    
    -0.76
    bewerken
    -0.69
     Theſe
    -0.69
    URLException
    -0.68
    ]--;
    -0.68
    帖最后由
    -0.68
    Coordonnées
    -0.67
    addPreferredGap
    -0.66
    Havolalar
    -0.64
     Anſ
    -0.64
    POSITIVE LOGITS
    content
    2.96
     content
    2.51
    Content
    2.21
     Content
    2.13
     CONTENT
    1.94
    CONTENT
    1.93
     contenido
    1.61
     conteúdo
    1.50
    getContent
    1.47
     contenu
    1.39
    Activations Density 0.058%

    No Known Activations