© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12350
    Prev
    Next
    INDEX
    Explanations

    instances of the word "discovered" and its variations, along with other related contextual keywords

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

    "discovered" or "found"

    np_acts-logits-general · gemini-2.0-flash

    finding discoveries

    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
     enví
    -0.51
    ArrowToggle
    -0.45
    kwür
    -0.43
     ligiloj
    -0.43
    новниш
    -0.43
    \{\\
    -0.42
     Romains
    -0.42
    nellement
    -0.41
     TestBed
    -0.40
     noDo
    -0.40
    POSITIVE LOGITS
     discovered
    1.05
    discovered
    0.98
     found
    0.94
     Discovered
    0.91
     Found
    0.86
     discovers
    0.83
     discovery
    0.82
    found
    0.82
     discovering
    0.80
     discoveries
    0.80
    Activations Density 0.426%

    No Known Activations