© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13728
    Prev
    Next
    INDEX
    Explanations

    references to characters dealing with trauma or hardship

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

    Superpowers or supernatural abilities

    np_acts-logits-general · gemini-2.0-flash

    superhuman abilities and transformations

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    FailureListener
    -0.48
     Unwin
    -0.46
    urança
    -0.41
    heça
    -0.41
     campagna
    -0.41
    drawiam
    -0.40
     Pembangunan
    -0.40
     cultuur
    -0.39
    epik
    -0.39
     aDecoder
    -0.39
    POSITIVE LOGITS
    MLLoader
    0.55
    ChildScrollView
    0.52
    OGND
    0.50
    IContainer
    0.48
    ThroughAttribute
    0.48
     BrowserModule
    0.47
     IBOutlet
    0.46
    UserScript
    0.45
     useState
    0.44
     Exacts
    0.44
    Activations Density 0.320%

    No Known Activations