© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6305
    Prev
    Next
    INDEX
    Explanations

    phrases that describe roles and contributions in collaborative work or research

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

    Follows the word "of"

    np_acts-logits-general · gemini-2.0-flash

    of followed by proper nouns or determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.68
     Reſ
    -0.67
     Conſ
    -0.65
     purpoſe
    -0.64
     myſelf
    -0.63
     Anſ
    -0.63
     autorytatywna
    -0.63
     uſe
    -0.60
     nahilalakip
    -0.60
    verwijspagina
    -0.59
    POSITIVE LOGITS
     of
    0.45
    ConstraintMaker
    0.41
    fromCharCode
    0.41
     Vielzahl
    0.36
    InstrumentedTest
    0.35
    OGND
    0.33
    __":
    0.32
    BeginInit
    0.31
    󠁣
    0.30
    ://$
    0.30
    Activations Density 1.241%

    No Known Activations