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. 10-GEMMASCOPE-RES-16K
    6. 12554
    Prev
    Next
    INDEX
    Explanations

    occurrences of meetings and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="'.$
    -0.73
     defStyle
    -0.69
    ]));
    
    -0.66
    солю
    -0.65
    ")));
    
    -0.65
    virons
    -0.64
    }));
    
    -0.64
    جمة
    -0.64
     TAMBÉM
    -0.64
    )));
    
    -0.64
    POSITIVE LOGITS
     meetings
    1.36
     Meetings
    1.25
     meeting
    1.15
    Meetings
    1.15
     Meeting
    1.14
    meetings
    1.10
    Meeting
    1.02
    meeting
    1.01
     MEETING
    0.96
     kasarigan
    0.89
    Activations Density 0.084%

    No Known Activations