© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14848
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate ongoing or simultaneous actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.61
    ніципалі
    -0.61
    joining
    -0.57
    Joining
    -0.56
     Joining
    -0.56
     joining
    -0.54
     pinulongan
    -0.53
    Rhestr
    -0.51
    rdı
    -0.50
     ritrov
    -0.48
    POSITIVE LOGITS
     asleep
    0.82
    wijl
    0.78
     waiting
    0.77
    ViewFeatures
    0.76
     away
    0.75
     sedang
    0.75
     awaiting
    0.75
     underway
    0.72
     preparing
    0.69
      (
    0.69
    Activations Density 0.176%

    No Known Activations