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. 4-GEMMASCOPE-RES-16K
    6. 786
    Prev
    Next
    INDEX
    Explanations

    instructions related to laboratory procedures and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.60
     aceptas
    -0.58
    ὺς
    -0.57
    BeginContext
    -0.56
    Responsive
    -0.55
    Chham
    -0.55
     Thrust
    -0.52
    delli
    -0.51
     Sizing
    -0.50
    Rail
    -0.50
    POSITIVE LOGITS
     ComVisible
    0.64
     stand
    0.62
    躇
    0.61
    bitat
    0.60
     typelib
    0.60
     reposer
    0.59
     WebDriverWait
    0.56
     CWE
    0.56
     standing
    0.55
     UnityEditor
    0.54
    Activations Density 0.759%

    No Known Activations