© 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. 6-GEMMASCOPE-RES-16K
    6. 2264
    Prev
    Next
    INDEX
    Explanations

    the word "OK" and its variations, indicating agreement or acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    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
     ‘
    -0.76
     autorytatywna
    -0.76
     useNavigate
    -0.74
     Berge
    -0.71
    δη
    -0.70
    `;
    
    -0.70
    )");
    
    -0.67
    ("-");
    -0.67
    ).
    
    -0.66
    POSITIVE LOGITS
     OK
    1.76
     ok
    1.71
     Ok
    1.61
    Ok
    1.56
     okay
    1.48
     alright
    1.47
    OK
    1.46
    ok
    1.39
     OKAY
    1.38
     Alright
    1.34
    Activations Density 0.036%

    No Known Activations