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. 24-GEMMASCOPE-RES-16K
    6. 4548
    Prev
    Next
    INDEX
    Explanations

    information related to software updates and subscription options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Software update notifications and downloads

    np_acts-logits-general · gemini-2.0-flash

    application features and availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -1.42
    <h3>
    -1.34
    ();*/
    -1.10
    <b>
    -1.07
    ;*/
    -1.02
     […]
    -0.99
    );*/
    -0.88
    */
    
    -0.86
     \\
    -0.86
    <h4>
    -0.83
    POSITIVE LOGITS
    </strong>
    4.15
    </b>
    2.63
    </u>
    1.62
    }$}
    1.36
    $}
    1.26
    </h4>
    1.25
    }{
    1.21
    </h2>
    1.19
    "}
    1.18
     }
    1.14
    Activations Density 0.120%

    No Known Activations