© 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
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1296
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ignore" and its variations

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

    the word "ignore" in technical documentation and code comments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    instructions or statements about disregarding or not taking something into account.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.55
    WEBPACK
    -0.47
    InputBorder
    -0.44
     AssemblyProduct
    -0.44
    MigrationBuilder
    -0.43
    XmlAccessorType
    -0.42
     otomatig
    -0.42
     استنادى
    -0.40
    localctx
    -0.39
    ISODE
    -0.39
    POSITIVE LOGITS
     ignore
    1.50
     ignored
    1.43
     Ignore
    1.42
     ignoring
    1.41
     ignores
    1.37
    Ignore
    1.35
    ignore
    1.32
     Ignoring
    1.31
    Ignoring
    1.21
    ignored
    1.16
    Activations Density 0.342%

    No Known Activations