Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 14976
    Prev
    Next
    INDEX
    Explanations

    expressions of trust and trustworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     Anaconda
    -0.91
    internalType
    -0.83
    Рабо
    -0.82
     barbarous
    -0.81
     EDS
    -0.81
     Specimens
    -0.80
    Shotgun
    -0.80
    onedDateTime
    -0.79
     Benito
    -0.78
     Derivatives
    -0.77
    POSITIVE LOGITS
     trust
    2.06
     Trust
    2.00
    Trust
    1.98
    TRUST
    1.93
    trust
    1.92
     TRUST
    1.91
     trusts
    1.82
     Trusts
    1.56
     trusting
    1.51
     trusted
    1.45
    Activations Density 0.043%

    No Known Activations