© 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. 22-GEMMASCOPE-RES-16K
    6. 16356
    Prev
    Next
    INDEX
    Explanations

    specific coding syntax or structure in programming or data-related contexts

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

    Code, questions, or optional features

    np_acts-logits-general · gemini-2.0-flash

    code comments and technical details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ();
    
    -0.50
    .",
    
    -0.49
     {},
    
    -0.47
    %;
    
    -0.47
    %
    
    -0.45
    SQLiteDatabase
    -0.45
     {};
    
    -0.45
     [];
    
    -0.43
     keyPressed
    -0.43
    $.
    
    -0.42
    POSITIVE LOGITS
    }*/
    2.06
    */
    2.05
     */
    1.89
    */
    
    1.70
    ();*/
    1.54
    );*/
    1.53
    }*/
    
    1.52
    )*/
    1.51
    </h6>
    1.51
    </h5>
    1.50
    Activations Density 0.261%

    No Known Activations