© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3897
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical functions and their properties

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

    Mathematical optimization: argmin, objective, minimize

    np_acts-logits-general · gemini-2.0-flash

    minimize or maximize objective function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.69
    yntaxException
    -0.64
    ineno
    -0.59
    .*")]
    -0.58
    oredCriteria
    -0.56
    tableFuture
    -0.53
     AssemblyCompany
    -0.53
    |}{
    -0.51
    коменду
    -0.51
    牌
    -0.50
    POSITIVE LOGITS
    minimize
    0.87
    Minimize
    0.82
     minimization
    0.80
     objective
    0.80
     minimizing
    0.78
     minimize
    0.78
    maximize
    0.74
     Minimize
    0.74
    Objective
    0.71
    Maximize
    0.70
    Activations Density 1.084%

    No Known Activations