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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9960
    Prev
    Next
    INDEX
    Explanations

    blocks of code in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    WebServlet
    -0.67
     GenerationType
    -0.64
    agisse
    -0.62
    دانشنامهٔ
    -0.61
    %;
    
    -0.60
     off
    -0.58
     prof
    -0.58
    <>
    
    -0.55
     sa
    -0.55
     =
    
    -0.53
    POSITIVE LOGITS
    }
    1.20
    )
    0.95
    </
    0.91
    </tr>
    0.90
    }.
    0.88
    </tbody>
    0.86
    }`).
    0.85
    ]
    0.84
    });
    0.83
    }).
    0.83
    Activations Density 0.062%

    No Known Activations