© 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. 37-GEMMASCOPE-RES-16K
    6. 3904
    Prev
    Next
    INDEX
    Explanations

    phrases related to questions and troubleshooting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.88
    AndEndTag
    -0.88
     Infórmanos
    -0.75
    存于互联网档案馆
    -0.75
    httphttps
    -0.73
    verifyException
    -0.71
     iNdEx
    -0.70
     CreateTagHelper
    -0.70
     transfieras
    -0.69
    WebVitals
    -0.68
    POSITIVE LOGITS
     Bearing
    0.47
    having
    0.46
    Having
    0.46
    £
    0.45
     Having
    0.44
     having
    0.43
     ș
    0.43
     equally
    0.43
    Bearing
    0.42
     apart
    0.41
    Activations Density 0.235%

    No Known Activations