© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4233
    Prev
    Next
    INDEX
    Explanations

    phrases and constructs that include the word "of."

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

    Follows "of"

    np_acts-logits-general · gemini-2.0-flash

    following 'of' for many phrases

    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
    mtd
    -0.46
    BirthDate
    -0.43
    ://
    -0.43
     Bod
    -0.42
    linux
    -0.40
    Gender
    -0.40
     Lind
    -0.40
    eseed
    -0.39
    Sparse
    -0.39
    Bod
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.74
     تكبرها
    0.60
    setVerticalGroup
    0.60
    ⓧ
    0.57
    ChildScrollView
    0.57
     typelib
    0.56
     utafitiHapana
    0.56
    mobileqq
    0.54
    IntoConstraints
    0.54
    complexContent
    0.54
    Activations Density 0.665%

    No Known Activations