© 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. 21367
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate patterns, connections, or notable events in a narrative context

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

    like or such as examples

    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
    rungsseite
    -0.84
     initComponents
    -0.72
     <",
    -0.69
    parsedMessage
    -0.65
     propOrder
    -0.63
    FieldOffsetTable
    -0.60
    IntoConstraints
    -0.59
     témoig
    -0.58
     EconPapers
    -0.58
     TestBed
    -0.58
    POSITIVE LOGITS
     подоб
    0.45
    こういう
    0.41
     such
    0.36
     böyle
    0.35
     solcher
    0.35
     like
    0.33
     slike
    0.33
    artigen
    0.32
     solche
    0.32
    artiges
    0.32
    Activations Density 0.053%

    No Known Activations