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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7124
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "here"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     Ethiopian
    -0.55
     опро
    -0.52
     Tibetan
    -0.52
     Gogh
    -0.51
    ندق
    -0.49
     PD
    -0.49
     Activision
    -0.49
    granate
    -0.49
     Draft
    -0.49
     POW
    -0.48
    POSITIVE LOGITS
    here
    1.23
     here
    1.17
    Here
    1.16
     Here
    1.16
    HERE
    1.09
     HERE
    1.06
     aquí
    1.04
     tää
    1.02
     Aquí
    1.02
    Aqui
    0.90
    Activations Density 0.054%

    No Known Activations