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. 3-GEMMASCOPE-RES-16K
    6. 12724
    Prev
    Next
    INDEX
    Explanations

    punctuation and blockquote elements, indicating structured text or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ষ্
    -0.62
    CascadeType
    -0.61
     nang
    -0.58
     color
    -0.57
     test
    -0.57
     rest
    -0.56
    lant
    -0.56
     fest
    -0.55
    AMED
    -0.53
    잔
    -0.53
    POSITIVE LOGITS
    </blockquote>
    3.30
    \]
    1.56
    </h5>
    1.50
    }`;
    1.50
    )";
    1.49
    </code>
    1.48
    </h1>
    1.42
    .";
    1.41
    `;
    1.40
    </td>
    1.38
    Activations Density 0.136%

    No Known Activations