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. 21-GEMMASCOPE-RES-16K
    6. 7045
    Prev
    Next
    INDEX
    Explanations

    phrases related to the process and efficiency of drilling operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.72
     []:
    -0.61
     BorderSide
    -0.60
     مرئيه
    -0.57
     disambiguazione
    -0.57
    Demografie
    -0.56
    reszcie
    -0.55
    UserScript
    -0.55
    XmlAccessType
    -0.55
    abestanden
    -0.55
    POSITIVE LOGITS
     rounds
    1.22
     cycles
    1.09
     round
    1.08
     session
    1.06
     cycle
    1.04
     run
    1.04
     sessions
    1.02
     passes
    1.02
     pass
    1.01
     iterations
    1.00
    Activations Density 0.826%

    No Known Activations