© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 587
    Prev
    Next
    INDEX
    Explanations

    mentions of the character "Cha" or variations of its name

    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
     étranger
    -0.46
     propOrder
    -0.45
     Eigentü
    -0.45
    хьтан
    -0.44
     Internasional
    -0.39
    httphttps
    -0.39
    underground
    -0.39
    TemporalType
    -0.38
     dAtA
    -0.38
     Erwartungen
    -0.38
    POSITIVE LOGITS
     Cha
    0.71
    Cha
    0.69
     cha
    0.63
     CHA
    0.60
     CreateTagHelper
    0.49
    cha
    0.46
     Chas
    0.42
    Chas
    0.42
     CHAM
    0.42
    Cham
    0.41
    Activations Density 0.187%

    No Known Activations