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. 2-GEMMASCOPE-RES-16K
    6. 14866
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "command"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }');
    -0.62
     Lagi
    -0.58
    ;");
    -0.57
    ."));
    -0.57
     PCP
    -0.57
    
    -0.57
    ใช่
    -0.56
    )");
    
    -0.55
    ]');
    -0.55
    اطر
    -0.55
    POSITIVE LOGITS
     command
    3.55
     Command
    3.46
    command
    3.29
    Command
    3.24
     COMMAND
    3.09
     commands
    2.97
    COMMAND
    2.84
     Commands
    2.78
    commands
    2.65
     commanded
    2.53
    Activations Density 0.029%

    No Known Activations