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. 1224
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax or command structures in code

    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
    httphttps
    -0.68
    expandindo
    -0.68
    ReusableCell
    -0.66
    yntaxException
    -0.63
    Билгалдахарш
    -0.62
     Chwiliwch
    -0.60
    Hentet
    -0.59
    addGap
    -0.59
     iprot
    -0.58
     insuffisamment
    -0.57
    POSITIVE LOGITS
     its
    0.42
             
    0.41
     Its
    0.39
    ¦
    0.39
    Its
    0.36
          
    0.33
     PIER
    0.32
    ,--
    0.32
       
    0.32
    ,»
    0.31
    Activations Density 0.292%

    No Known Activations