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. 20-GEMMASCOPE-RES-16K
    6. 3589
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements, likely focusing on typical structure and operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, non-English, or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    Lighthill efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     end
    -1.14
     End
    -1.07
     END
    -1.03
    End
    -0.91
    end
    -0.88
    END
    -0.83
     ends
    -0.79
     kasarigan
    -0.74
     Ende
    -0.72
     ended
    -0.69
    POSITIVE LOGITS
    }
    0.56
    Witam
    0.52
    وردار
    0.50
     }
    0.49
    ManagedBean
    0.49
     écl
    0.49
    Biographie
    0.47
    blockList
    0.44
    Smarty
    0.44
    DeleteMapping
    0.44
    Activations Density 0.145%

    No Known Activations