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. 8-GEMMASCOPE-RES-16K
    6. 14947
    Prev
    Next
    INDEX
    Explanations

    the presence of specific structural markers indicating the start of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -1.23
     виправивши
    -0.95
    AsUp
    -0.89
    Према
    -0.88
    GraphicsUnit
    -0.86
    脚注の使い方
    -0.85
    }$​
    -0.83
     дописавши
    -0.82
     ]
    
    -0.81
    )}</
    -0.78
    POSITIVE LOGITS
     width
    0.66
    width
    0.55
     Width
    0.53
     шири
    0.52
     WIDTH
    0.50
    Aware
    0.49
    Width
    0.48
     largeur
    0.46
    WIDTH
    0.45
    height
    0.44
    Activations Density 0.028%

    No Known Activations