© 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. 31-GEMMASCOPE-RES-16K
    11. 4067
    Prev
    Next
    INDEX
    Explanations

    references to possessive pronouns

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

    possessive pronouns referring to personal responsibility or ownership (e.g., "your").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.54
    AccessorTable
    -0.50
    UrlResolution
    -0.48
    неопр
    -0.46
     esternos
    -0.45
    jalá
    -0.44
    seteq
    -0.43
    bibfield
    -0.43
    anyahu
    -0.42
     pouvoit
    -0.41
    POSITIVE LOGITS
     own
    0.51
    所
    0.47
     another
    0.46
    readyState
    0.45
     performances
    0.43
     candidature
    0.42
     ulter
    0.41
     useDispatch
    0.41
     respective
    0.41
     ellen
    0.41
    Activations Density 0.277%

    No Known Activations