© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4178
    Prev
    Next
    INDEX
    Explanations

    terms describing efficiency, effectiveness, and stability in various contexts

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

    Describes something as efficient or robust

    np_acts-logits-general · gemini-2.0-flash

    degree of sufficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #![
    -0.52
    LookAnd
    -0.51
    MLLoader
    -0.48
     препратки
    -0.46
     виправивши
    -0.46
    InputTagHelper
    -0.46
     BehaviorSubject
    -0.45
     <=",
    -0.42
     vVar
    -0.40
     getIs
    -0.40
    POSITIVE LOGITS
     enough
    1.05
    enough
    0.93
     Enough
    0.84
     ביותר
    0.82
     genug
    0.82
    Enough
    0.81
     للغاية
    0.77
     ENOUGH
    0.75
    ness
    0.75
     genoeg
    0.70
    Activations Density 1.475%

    No Known Activations