© 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. 12-GEMMASCOPE-RES-16K
    6. 5840
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to stretching and elasticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.47
     intptr
    -0.44
     carbón
    -0.44
    Personensuche
    -0.41
     lluvia
    -0.40
     []:
    -0.39
    AsUp
    -0.38
     mensaj
    -0.37
     bubuk
    -0.37
     Савезне
    -0.35
    POSITIVE LOGITS
     stretch
    1.58
     Stretch
    1.51
    stretch
    1.49
     stretching
    1.44
    Stretch
    1.41
     Stretching
    1.39
     stretched
    1.38
    stret
    1.34
     stretches
    1.31
    Stret
    1.30
    Activations Density 0.271%

    No Known Activations