© 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. 10637
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate incompletion or pending actions

    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
     препратки
    -0.45
    rítica
    -0.44
    addComponent
    -0.38
     Bestand
    -0.37
    Hochspringen
    -0.36
    祇
    -0.35
     increasingly
    -0.35
    ่าง
    -0.35
     Krom
    -0.35
     yyr
    -0.35
    POSITIVE LOGITS
     هنوز
    0.89
    まだ
    0.81
     yet
    0.81
    還沒
    0.79
    还没有
    0.77
    尚未
    0.76
    还没
    0.76
     belum
    0.75
    还未
    0.75
     Belum
    0.75
    Activations Density 0.244%

    No Known Activations