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

    Neuronpedia

    Jacobian LensNEW
    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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102905
    Prev
    Next
    INDEX
    Explanations

    interactions and requests related to relationships and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    KURZBESCHREIBUNG
    -0.41
    <?
    -0.39
     rainha
    -0.39
    XmlAccessorType
    -0.38
     Mandatory
    -0.37
     Compulsory
    -0.36
    جوايز
    -0.35
     desaf
    -0.35
     conditioning
    -0.35
     gewohnt
    -0.34
    POSITIVE LOGITS
    FieldBuilder
    0.56
     pageContext
    0.52
    reactstrap
    0.47
    尚
    0.45
     ModelExpression
    0.44
    ScopeManager
    0.43
    ußer
    0.42
     niên
    0.41
     Stell
    0.40
    preference
    0.40
    Activations Density 0.078%

    No Known Activations