© 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. 93035
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs indicating a personal narrative

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

    starts with a pronoun or 'Dear'

    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
     kohdetta
    -0.35
    Autoritní
    -0.33
     næste
    -0.31
     nächste
    -0.30
    Geplaatst
    -0.30
     Racing
    -0.28
     tomorrow
    -0.28
    ībā
    -0.28
     next
    -0.27
     poursuite
    -0.27
    POSITIVE LOGITS
     betweenstory
    0.90
    ScopeManager
    0.69
    WithIOException
    0.68
    VYMaps
    0.65
    ValueStyle
    0.61
     IFTT
    0.57
     AssemblyTitle
    0.56
    RegressionTest
    0.54
    ectady
    0.54
     ujednoznacz
    0.54
    Activations Density 0.202%

    No Known Activations