© 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. 28-GEMMASCOPE-RES-16K
    11. 4809
    Prev
    Next
    INDEX
    Explanations

    verbs related to arrival or movement towards a specific destination

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

    "Come" or "viens" followed by preposition

    np_acts-logits-general · gemini-2.0-flash

    come and coming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     judiciaire
    -0.43
    eachtet
    -0.42
     credere
    -0.42
     stessi
    -0.40
    CompleteListener
    -0.39
    PerformLayout
    -0.38
    ectores
    -0.38
     olho
    -0.38
    Portály
    -0.37
    yentes
    -0.37
    POSITIVE LOGITS
    Tikang
    0.56
     wireType
    0.55
     متعلقه
    0.53
    CreateModel
    0.53
    interopRequire
    0.52
    Come
    0.52
    came
    0.51
    ⓧ
    0.49
    Came
    0.48
     Come
    0.47
    Activations Density 0.149%

    No Known Activations