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-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 1176
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and behaviors, particularly those associated with performing or executing acts

    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
    SharedCtor
    -0.49
    ierung
    -0.45
    Демографія
    -0.42
     BrowserModule
    -0.41
    Życiorys
    -0.41
    Dichloroethane
    -0.40
    SpringBootTest
    -0.40
     Италијани
    -0.39
    UseVisualStyle
    -0.39
    aruhi
    -0.39
    POSITIVE LOGITS
    uation
    0.54
    Ӕ
    0.49
    uary
    0.48
    /**
    0.46
     vectorielles
    0.46
    IVATE
    0.44
     TAMBÉM
    0.43
     act
    0.42
    sweise
    0.42
     upon
    0.40
    Activations Density 0.171%

    No Known Activations