© 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. 12-GEMMASCOPE-RES-16K
    11. 1210
    Prev
    Next
    INDEX
    Explanations

    personal references and expressions of connection to others

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

    first-person possessive pronouns and personal narrative language.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language signaling a first-person point of view, particularly collective self-reference and possession.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Umständen
    -0.35
    EndGlobal
    -0.34
    rendre
    -0.33
    assertNotNull
    -0.31
    lido
    -0.30
     yym
    -0.30
    edy
    -0.29
    ilich
    -0.29
     Schmid
    -0.29
     Schiller
    -0.28
    POSITIVE LOGITS
     تضيفلها
    0.61
     viſ
    0.58
    зулта
    0.54
     الاطلاع
    0.53
    BeginContext
    0.52
    󠁢
    0.52
    oredCriteria
    0.51
     defaultstate
    0.50
    invokeLater
    0.49
    ComponentScan
    0.49
    Activations Density 1.061%

    No Known Activations