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. 11092
    Prev
    Next
    INDEX
    Explanations

    mathematical constants and terms related to limits and bounds in equations

    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
    ReusableCell
    -0.69
    AddTagHelper
    -0.67
    Hentet
    -0.64
    minecraftforge
    -0.60
    ImageContext
    -0.59
     Voulez
    -0.57
     Balth
    -0.56
    glTexCoord
    -0.55
     Balt
    -0.54
     opérés
    -0.53
    POSITIVE LOGITS
      
    0.75
     ‏
    0.63
     ‎
    0.63
    ​​​​
    0.62
     fué
    0.58
     justamente
    0.58
     

    0.58
    ]?.
    0.58
    ‍♀️
    0.57
     also
    0.57
    Activations Density 0.157%

    No Known Activations