© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 50677
    Prev
    Next
    INDEX
    Explanations

    elements related to structured information and references

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

    section headers and references

    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
     externi
    -0.44
     betweenstory
    -0.40
    condu
    -0.37
    LabelTagHelper
    -0.37
     تضيفلها
    -0.36
    oprop
    -0.35
    πι
    -0.34
    marke
    -0.34
     steering
    -0.34
    abil
    -0.34
    POSITIVE LOGITS
    ThroughAttribute
    0.63
    Portail
    0.62
     autorytatywna
    0.60
    GEBURTSDATUM
    0.53
    NameInMap
    0.51
    Derbyniad
    0.51
    }{*}{}
    0.49
     pinulongan
    0.48
    เช่น
    0.48
    MemoryWarning
    0.47
    Activations Density 0.004%

    No Known Activations