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. 20-GEMMASCOPE-RES-16K
    6. 11748
    Prev
    Next
    INDEX
    Explanations

    terms related to theoretical physics concepts and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Potential", especially in physics/mathematics contexts

    np_acts-logits-general · gemini-2.0-flash

    random quenched potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.81
     AspNetCore
    -0.61
    (\%)
    -0.60
     INDUSTR
    -0.60
    NullException
    -0.59
     Blanchard
    -0.58
     Aachen
    -0.58
    rceil
    -0.57
    ladesh
    -0.56
    glog
    -0.56
    POSITIVE LOGITS
     potential
    0.81
    Potential
    0.76
     Potential
    0.71
    potential
    0.66
    XmlAccessorType
    0.66
     potentiel
    0.61
     potentials
    0.61
     potencial
    0.59
    StoryboardSegue
    0.58
     POTENTIAL
    0.57
    Activations Density 1.072%

    No Known Activations