© 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. 13642
    Prev
    Next
    INDEX
    Explanations

    terms related to reservation and resolution in a technical or organizational context

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

    "resolve" or "reserve" followed by specific characters

    np_acts-logits-general · gemini-2.0-flash

    reserve / resolve

    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
     getPage
    -0.52
     getPath
    -0.50
    paravant
    -0.48
    Italy
    -0.48
    Email
    -0.47
    ToDelete
    -0.46
    Android
    -0.46
    Team
    -0.46
    Mary
    -0.45
    Equation
    -0.45
    POSITIVE LOGITS
     reserve
    0.66
    ^*)
    0.60
     Resolve
    0.59
    OGND
    0.59
     Reserved
    0.59
    resolve
    0.58
     observing
    0.58
    reserve
    0.58
     resolve
    0.56
     Reserve
    0.56
    Activations Density 0.190%

    No Known Activations