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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 4919
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "current" in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defStyle
    -0.73
    DeleteBehavior
    -0.68
     mkdir
    -0.68
     SignUp
    -0.65
    DockStyle
    -0.65
     Sodom
    -0.64
    mkdir
    -0.64
    ExecuteReader
    -0.63
    quedas
    -0.63
     Réponses
    -0.62
    POSITIVE LOGITS
    current
    4.36
     current
    4.26
     Current
    3.77
    Current
    3.72
     CURRENT
    3.41
    CURRENT
    3.36
     curent
    2.69
     aktuellen
    2.36
    urrent
    2.32
     currents
    2.29
    Activations Density 0.090%

    No Known Activations