© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 123528
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Our" and variations of it as a possessive pronoun in different contexts

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

    sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.94
    KommentareTeilen
    -0.84
     Administrativna
    -0.82
     zwiſchen
    -0.79
    expandindo
    -0.79
     snippetHide
    -0.78
    IUrlHelper
    -0.78
    Хьажоргаш
    -0.76
    twimg
    -0.76
     CallOverrides
    -0.76
    POSITIVE LOGITS
    째
    0.30
    In
    0.28
     autorytatywna
    0.26
    ssä
    0.24
    If
    0.24
    Four
    0.23
     carreaux
    0.23
     canadienne
    0.23
    ცი
    0.22
     mauvaise
    0.22
    Activations Density 0.111%

    No Known Activations