© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7696
    Prev
    Next
    INDEX
    Explanations

    components associated with lists and item management actions

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

    Strings followed by "name"

    np_acts-logits-general · gemini-2.0-flash

    android string resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colspan
    -0.45
    extAlignment
    -0.38
     Ehr
    -0.38
     continuidad
    -0.36
    TagHelpers
    -0.35
    ulir
    -0.34
     mathvariant
    -0.32
    AppCompat
    -0.32
     GenerationType
    -0.32
    BitmapFactory
    -0.31
    POSITIVE LOGITS
    aarrggbb
    0.81
    LookAnd
    0.77
    InstrumentedTest
    0.68
    httphttps
    0.66
    SourceChecksum
    0.66
     nahilalakip
    0.63
    ंदीखरीदारी
    0.59
    -------
    0.59
    makeConstraints
    0.57
    StoryboardSegue
    0.57
    Activations Density 0.329%

    No Known Activations