© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 16371
    Prev
    Next
    INDEX
    Explanations

    references to possession and ownership

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

    Possessive pronouns preceding nouns

    np_acts-logits-general · gemini-2.0-flash

    possessive determiners followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -0.84
     themselves
    -0.81
     yourselves
    -0.78
     himself
    -0.74
     herself
    -0.73
    #+#
    -0.71
    itself
    -0.69
    themselves
    -0.65
     oneself
    -0.63
    herself
    -0.63
    POSITIVE LOGITS
     exact
    0.63
     للمعارف
    0.63
    exact
    0.55
    ArrowToggle
    0.54
    colgroup
    0.53
    \{\\
    0.52
     eventual
    0.51
    <%=
    0.51
    ]").
    0.51
     behalf
    0.50
    Activations Density 0.296%

    No Known Activations