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. 12032
    Prev
    Next
    INDEX
    Explanations

    instances of the word "end" or its variations, indicating a focus on conclusions or final outcomes

    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
    aronder
    -0.77
    KommentareTeilen
    -0.76
    Bibliograf
    -0.75
    ]),
    
    -0.73
    "));
    
    -0.73
    })));
    -0.73
    MENAFN
    -0.71
    ()?;
    -0.71
    ">
    
    
    -0.70
     [];
    
    -0.69
    POSITIVE LOGITS
     ended
    2.15
     ends
    2.02
     ending
    2.02
     Ending
    1.93
     Ends
    1.87
     Ended
    1.81
    Ending
    1.74
     endings
    1.69
    Ended
    1.66
    ended
    1.53
    Activations Density 0.057%

    No Known Activations