© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10863
    Prev
    Next
    INDEX
    Explanations

    code-related elements or syntax structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lath
    -0.90
     Efq
    -0.87
     Hemis
    -0.86
    ••••
    -0.86
     Koz
    -0.78
     testData
    -0.77
    ftant
    -0.76
    ••
    -0.76
     Leland
    -0.75
    ykite
    -0.75
    POSITIVE LOGITS
    </code>
    2.12
    }`
    1.15
    </s>
    1.14
    )`
    1.13
    </th>
    1.12
    })));
    1.10
    `,
    1.08
    }`)
    1.03
    </blockquote>
    1.03
    </i>
    1.01
    Activations Density 0.134%

    No Known Activations