© 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-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7778
    Prev
    Next
    INDEX
    Explanations

    phrases related to standing up or advocating for something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.55
    
    -0.49
    windowFixed
    -0.46
    MemoryWarning
    -0.41
    emlrt
    -0.40
    $_['
    -0.40
     OBB
    -0.38
    RegressionTest
    -0.38
    hw
    -0.37
    Marc
    -0.37
    POSITIVE LOGITS
     tall
    0.82
     stand
    0.82
     Stand
    0.81
    Stand
    0.77
     STAND
    0.70
     debout
    0.70
     stood
    0.70
     taller
    0.68
     Tall
    0.67
     tallest
    0.66
    Activations Density 0.064%

    No Known Activations