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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9086
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to research methods and ethical considerations in scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -0.61
    accharides
    -0.55
    
    -0.53
     weten
    -0.53
    localPosition
    -0.52
    Hrsg
    -0.52
     pourrais
    -0.51
     doInBackground
    -0.51
     województwie
    -0.51
    itulo
    -0.50
    POSITIVE LOGITS
     ujednoznacz
    0.83
    IContainer
    0.72
    ">//
    0.69
     preocupes
    0.66
     tijds
    0.66
     PropertyChanged
    0.64
     Chess
    0.64
    tschafts
    0.63
     Petri
    0.62
     Tric
    0.61
    Activations Density 2.320%

    No Known Activations