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. 9780
    Prev
    Next
    INDEX
    Explanations

    distinct structural elements or markers typically found in coded documents

    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
    NUMX
    -1.26
    protoimpl
    -1.12
     ་་
    -1.08
     Efq
    -1.05
     propOrder
    -0.99
     سكانية
    -0.97
    \<^
    -0.96
     ―――――
    -0.94
    esterday
    -0.94
     Jefus
    -0.94
    POSITIVE LOGITS
    )
    0.82
    <eos>
    0.81
    ↵↵
    0.78
     />
    0.78
    ),
    0.76
    ]
    0.76
    ],
    0.74
    ).
    0.74
    ].
    0.72
    ↵
    0.71
    Activations Density 0.672%

    No Known Activations