© 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. 24-GEMMASCOPE-RES-16K
    6. 6056
    Prev
    Next
    INDEX
    Explanations

    references to trust and trustworthiness in relationships and interactions

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

    "trust" and its variations

    np_acts-logits-general · gemini-2.0-flash

    trust followed by us, in, and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ActionResult
    -0.43
    es
    -0.42
     grotesque
    -0.40
     sort
    -0.40
     Gor
    -0.40
     Zing
    -0.40
     Chou
    -0.39
    javadoc
    -0.39
     Sep
    -0.39
    [:]
    -0.39
    POSITIVE LOGITS
     trust
    1.09
     Trust
    1.06
     confianza
    1.05
     TRUST
    1.03
    Trust
    1.03
     confiança
    1.01
     Trusted
    0.95
    TRUST
    0.94
     confiance
    0.94
    trust
    0.94
    Activations Density 0.238%

    No Known Activations