© 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. 20-GEMMASCOPE-RES-16K
    6. 15532
    Prev
    Next
    INDEX
    Explanations

    phrases related to opposition and criticism in various contexts

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

    expressions of opposition, criticism, or controversy toward a decision, plan, or action.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    language expressing disagreement, criticism, or opposition to a proposal, plan, or policy.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    GEBURTSDATUM
    -0.52
     abstrait
    -0.47
    spesies
    -0.46
    OGND
    -0.46
     Manajemen
    -0.45
     CURIAM
    -0.44
     trésor
    -0.43
     okuyayım
    -0.42
    WindowConstants
    -0.42
     présidenti
    -0.42
    POSITIVE LOGITS
     objections
    0.71
     objection
    0.63
     objected
    0.59
    givings
    0.55
     doubts
    0.50
    MigrationBuilder
    0.49
     detra
    0.48
     concerns
    0.48
     Objection
    0.47
     negative
    0.47
    Activations Density 0.399%

    No Known Activations