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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7038
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a timeframe or sequence of events before a specific incident

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.43
    dă
    -0.37
    Mutable
    -0.36
    ItemLayout
    -0.36
    Xd
    -0.35
    tku
    -0.34
     Zuw
    -0.33
    ệ
    -0.32
     käytt
    -0.31
    Netz
    -0.31
    POSITIVE LOGITS
     before
    0.98
    before
    0.90
     antes
    0.86
    Before
    0.86
     Before
    0.85
     ennen
    0.84
     BEFORE
    0.83
    Перед
    0.82
    BEFORE
    0.79
     inför
    0.79
    Activations Density 0.238%

    No Known Activations