Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 14081
    Prev
    Next
    INDEX
    Explanations

    concepts related to effective modeling in physics, particularly regarding forces and potentials in colloidal systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.80
    prüche
    -0.58
    lankton
    -0.58
    ciatore
    -0.57
     فريبيس
    -0.55
    transport
    -0.53
     AspNetCore
    -0.52
    onnaissance
    -0.52
    سمبر
    -0.51
    devamını
    -0.51
    POSITIVE LOGITS
     potential
    0.93
    Potential
    0.85
    potential
    0.84
     Potential
    0.81
     attractive
    0.79
    IBOutlet
    0.72
     POTENTIAL
    0.72
     Attractive
    0.72
     potentiel
    0.71
    attractive
    0.71
    Activations Density 1.310%

    No Known Activations