© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 979
    Prev
    Next
    INDEX
    Explanations

    terms and symbols related to mathematical variables and equations in a theoretical physics context

    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
    expandindo
    -0.69
    CppMethod
    -0.67
     Obre
    -0.65
    AnchorStyles
    -0.62
    buc
    -0.60
    #+#
    -0.59
     latest
    -0.59
      
    -0.58
    backslash
    -0.58
    <b>
    -0.57
    POSITIVE LOGITS
    omega
    0.89
     Theta
    0.88
     Epsilon
    0.84
    Theta
    0.77
    transQ
    0.77
    theta
    0.74
     theta
    0.72
     omega
    0.71
     Wraith
    0.70
    iastes
    0.70
    Activations Density 0.741%

    No Known Activations