© 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. 5-GEMMASCOPE-RES-16K
    11. 10754
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of removal or reduction of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.95
    fjspx
    -0.85
     intptr
    -0.83
    RuleContext
    -0.80
     Preheat
    -0.79
    tvguidetime
    -0.79
    contentLoaded
    -0.78
    routeProvider
    -0.77
    TemporalType
    -0.75
    rungsseite
    -0.72
    POSITIVE LOGITS
     elimination
    1.45
    elimin
    1.35
     Elimination
    1.31
    Elimin
    1.25
     eliminate
    1.24
     eliminated
    1.22
     eliminating
    1.18
     elimin
    1.17
     eliminates
    1.06
     Eliminate
    1.06
    Activations Density 0.109%

    No Known Activations