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. 23-GEMMASCOPE-RES-16K
    6. 9077
    Prev
    Next
    INDEX
    Explanations

    elements related to news, updates, and schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ();*/
    -2.35
    </h6>
    -2.29
     */
    
    -2.18
    */
    
    -2.10
    );*/
    -2.08
    ;*/
    -2.04
    });*/
    -2.03
    }*/
    
    -2.02
    }*/
    -1.99
    )*/
    -1.90
    POSITIVE LOGITS
    </strong>
    1.32
    </b>
    0.72
    ↵↵
    0.58
     Дата
    0.42
     corse
    0.38
    جغرافيا
    0.36
    ”
    0.35
    http
    0.34
    ꒱
    0.34
    <u>
    0.34
    Activations Density 0.005%

    No Known Activations