© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7429
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or varying opinions from different groups of people

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

    Follows opinions or beliefs

    np_acts-logits-general · gemini-2.0-flash

    some people believe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Попис
    -0.61
    ########.
    -0.60
    DebuggerNonUser
    -0.45
    TableBody
    -0.45
    <?
    -0.44
    ArgsConstructor
    -0.43
     يتيمه
    -0.43
    ionales
    -0.42
    endregion
    -0.41
    GEBURTSDATUM
    -0.41
    POSITIVE LOGITS
     argue
    0.77
     speculate
    0.63
     argued
    0.56
     prefer
    0.56
     believe
    0.56
     speculated
    0.56
     think
    0.55
     suggest
    0.54
     denken
    0.54
     critics
    0.52
    Activations Density 0.258%

    No Known Activations