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. 8-GEMMASCOPE-RES-16K
    6. 4141
    Prev
    Next
    INDEX
    Explanations

    phrases related to obtaining or acquiring items or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trix
    -0.73
    ;#
    -0.66
     setTime
    -0.65
    affaires
    -0.64
    setName
    -0.63
     والص
    -0.63
    ervos
    -0.63
     play
    -0.62
     Says
    -0.62
     act
    -0.58
    POSITIVE LOGITS
    obtained
    1.56
     obtained
    1.55
     obtains
    1.53
     Obtaining
    1.48
     Obtained
    1.43
    Obtain
    1.43
     Obtain
    1.42
     obtain
    1.41
     obtaining
    1.32
    obtain
    1.29
    Activations Density 0.151%

    No Known Activations