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. 12509
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or figures within a scientific context

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

    Precedes a question mark or quote

    np_acts-logits-general · gemini-2.0-flash

    technical questions and code

    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
    __*/
    -0.77
     };
    -0.65
    ;}
    -0.65
     });
    
    -0.62
    .);
    -0.61
     };
    
    -0.60
     });
    -0.59
    -;
    -0.58
    !';
    -0.58
    *);
    -0.58
    POSITIVE LOGITS
    uxxxx
    0.63
    </caption>
    0.62
    <table>
    0.59
    Fazit
    0.57
    ""
    0.55
    期刊论文
    0.55
    "</
    0.54
    ellees
    0.53
    </
    0.52
     незавершена
    0.52
    Activations Density 0.124%

    No Known Activations