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. 8264
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or presence

    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
    missione
    -0.55
    ılan
    -0.54
     طریق
    -0.53
     कीजिए
    -0.51
    )):
    
    -0.51
    lawan
    -0.49
    ähig
    -0.48
    activated
    -0.48
    merate
    -0.48
    美味しかった
    -0.48
    POSITIVE LOGITS
    就
    1.07
     ModelExpression
    0.98
     же
    0.92
    便
    0.92
     भी
    0.91
    าก็
    0.91
    ก็
    0.87
    도
    0.86
     就
    0.86
     ก็
    0.84
    Activations Density 0.109%

    No Known Activations