© 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. 3-GEMMASCOPE-RES-16K
    6. 869
    Prev
    Next
    INDEX
    Explanations

    mentions of modal elements in a framework or coding context

    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
     nakalista
    -0.90
    )))
    
    -0.81
    PerformLayout
    -0.75
    Bioaccumulative
    -0.68
    BeginContext
    -0.67
    ]))
    
    -0.66
    }]
    
    -0.64
    GrantedAuthority
    -0.64
    Rhestr
    -0.63
     quý
    -0.63
    POSITIVE LOGITS
    modal
    3.32
     Modal
    3.08
    Modal
    3.00
     modal
    2.97
    MODAL
    2.53
    setModal
    1.61
    openModal
    1.42
    showModal
    1.39
     multimodal
    1.35
     modality
    1.32
    Activations Density 0.055%

    No Known Activations