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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 450
    Prev
    Next
    INDEX
    Explanations

    terms related to composition and combining elements or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réfrig
    -0.95
     Kars
    -0.86
    Demografía
    -0.84
     Varela
    -0.83
    }],
    
    -0.83
    IsPostBack
    -0.82
    ociação
    -0.81
    الحياه
    -0.81
     endforeach
    -0.81
     Khr
    -0.78
    POSITIVE LOGITS
     Compose
    1.02
     compose
    1.02
     compositions
    0.94
     composed
    0.92
    Compose
    0.92
    composed
    0.90
     composing
    0.90
     Composition
    0.88
    Compos
    0.87
     COMPOS
    0.86
    Activations Density 0.120%

    No Known Activations