© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 22243
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate equivalency or comparison

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

    statements of equivalence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagLayout
    -0.50
    catch
    -0.48
     Hols
    -0.47
     Charities
    -0.47
     bénévol
    -0.44
    BorderStyle
    -0.44
    Daddy
    -0.42
    JOH
    -0.42
    InInspector
    -0.42
    réhen
    -0.42
    POSITIVE LOGITS
     equivalent
    1.30
    Equivalent
    1.29
     Equivalent
    1.26
    equivalent
    1.25
     equivalence
    1.04
     equivalents
    1.01
     equivalente
    1.01
     equival
    0.99
     Equi
    0.86
    Equi
    0.86
    Activations Density 0.022%

    No Known Activations