© 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
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1168
    Prev
    Next
    INDEX
    Explanations

    phrases indicating unexpected outcomes or contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ówczas
    -0.46
    vrigt
    -0.46
    новништво
    -0.45
     fortemente
    -0.45
     Nuestro
    -0.44
     cursory
    -0.40
    SequentialGroup
    -0.40
    ungguhnya
    -0.39
     praça
    -0.39
    NamedQueries
    -0.39
    POSITIVE LOGITS
     getContext
    0.50
    最快更新
    0.47
     endblock
    0.46
    SpringBootTest
    0.43
     jspb
    0.42
    UserScript
    0.40
     getUserId
    0.40
     CURIAM
    0.40
    gdx
    0.40
    windowFixed
    0.40
    Activations Density 0.233%

    No Known Activations