© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7417
    Prev
    Next
    INDEX
    Explanations

    instances of conditional or sequential actions in a narrative context

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

    First-person perspective, past actions

    np_acts-logits-general · gemini-2.0-flash

    states of completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.63
    出版年
    -0.58
     justru
    -0.57
     never
    -0.55
    +#+
    -0.54
     също
    -0.53
    never
    -0.52
     jamás
    -0.52
    当時
    -0.51
    今から
    -0.50
    POSITIVE LOGITS
     initial
    0.96
     sufficiently
    0.87
     successful
    0.87
     selesai
    0.84
     satisfactory
    0.84
     successfully
    0.84
     finishes
    0.80
     satisfactorily
    0.79
     finished
    0.79
     sufficient
    0.78
    Activations Density 0.313%

    No Known Activations