© 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. 84223
    Prev
    Next
    INDEX
    Explanations

    words related to hierarchical structures and relationships among characters

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

    states and outcomes

    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
     zupeł
    -0.40
     bedo
    -0.40
     kanskje
    -0.39
     wynika
    -0.39
    Yes
    -0.39
     ianuarie
    -0.38
     gemeint
    -0.37
     achtergrond
    -0.36
    short
    -0.36
     ciągu
    -0.36
    POSITIVE LOGITS
     Administrativna
    0.87
    WithIOException
    0.69
    .*")]
    0.60
    MLLoader
    0.59
    TagHelpers
    0.57
     InputDecoration
    0.57
     IBOutlet
    0.54
    曖昧さ回避
    0.54
     ivelany
    0.53
     rehabilitate
    0.53
    Activations Density 0.142%

    No Known Activations