© 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. 30-GEMMASCOPE-RES-16K
    11. 12384
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or feelings of being overwhelmed

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

    "sounds" or "sound"

    np_acts-logits-general · gemini-2.0-flash

    sounds scary, familiar, odd, or crazy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desen
    -0.37
     noten
    -0.37
     arşivlendi
    -0.36
    MigrationBuilder
    -0.36
    раздо
    -0.36
    Manbalar
    -0.35
    ChildScrollView
    -0.35
    AfterEach
    -0.34
    jsonwebtoken
    -0.34
     sebaliknya
    -0.34
    POSITIVE LOGITS
     sounds
    1.17
    Sounds
    1.14
    sounds
    1.12
     Sounds
    1.12
     cliché
    1.04
     cliche
    1.03
     sounding
    0.92
     klingt
    0.90
     clich
    0.89
     sound
    0.86
    Activations Density 0.334%

    No Known Activations