© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 214
    Prev
    Next
    INDEX
    Explanations

    references to mobile games and gaming events

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

    Mobile game advertisements or gameplay

    np_acts-logits-general · gemini-2.0-flash

    mobile games

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ımıza
    -0.38
     squ
    -0.36
    RTCK
    -0.35
    rungsseite
    -0.35
    )_/¯
    -0.35
     dwind
    -0.33
     valg
    -0.33
    mış
    -0.33
    essica
    -0.32
     væ
    -0.32
    POSITIVE LOGITS
     gacha
    0.49
    Svara
    0.46
    twimg
    0.46
     initComponents
    0.45
    ſchaft
    0.43
    Externé
    0.42
     tower
    0.41
     rewards
    0.41
     Rewards
    0.41
    ایج
    0.41
    Activations Density 0.054%

    No Known Activations