© 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. 22-GEMMASCOPE-RES-16K
    6. 3599
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and actions related to navigation in web content

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

    HTML "href" tag

    np_acts-logits-general · gemini-2.0-flash

    web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.94
     Monfieur
    -0.92
     متعلقه
    -0.91
    ]';
    -0.89
    `;
    
    -0.88
     Anſ
    -0.87
     Diſ
    -0.83
     Eſ
    -0.81
    __":
    
    -0.81
     Theſe
    -0.80
    POSITIVE LOGITS
    javascript
    0.79
    #!/
    0.69
    ="#"
    0.63
     #
    0.63
    #
    0.62
     href
    0.62
     '#
    0.61
    ="#">
    0.59
    mailto
    0.59
     '#'
    0.59
    Activations Density 0.046%

    No Known Activations