© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116991
    Prev
    Next
    INDEX
    Explanations

    references to the Apache Felix SCR (Service Component Runtime) component

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     uğ
    -0.40
    RegressionTest
    -0.39
     drinks
    -0.34
     escra
    -0.34
     liquor
    -0.33
     oğ
    -0.33
     pubblic
    -0.32
    äfts
    -0.32
    empêcher
    -0.32
    ፩
    -0.31
    POSITIVE LOGITS
    stereotype
    1.52
     فريبيس
    0.77
    astéroïdes
    0.76
     Numerade
    0.65
    цездатний
    0.63
    NgModule
    0.63
     AssemblyTitle
    0.62
    NameInMap
    0.61
    RTGC
    0.61
    InjectMocks
    0.60
    Activations Density 0.000%

    No Known Activations