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

    Neuronpedia

    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. 14591
    Prev
    Next
    INDEX
    Explanations

    terms and references related to software applications and integration processes

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

    before suffixes like 's, +, can, will, with'

    np_acts-logits-general · gemini-2.0-flash

    configuring systems and operations

    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
     auroit
    -0.48
     feroit
    -0.47
     étoit
    -0.46
     avoient
    -0.42
     initComponents
    -0.40
     pouvoit
    -0.39
    Manbalar
    -0.36
    TagMode
    -0.35
    DockStyle
    -0.34
    ("")]
    -0.34
    POSITIVE LOGITS
    WebElementEntity
    0.60
    xase
    0.53
    alnız
    0.52
     Enhanced
    0.48
     personnel
    0.48
     audits
    0.48
    setopt
    0.48
     operational
    0.48
     partner
    0.47
    abbix
    0.47
    Activations Density 0.680%

    No Known Activations