© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3503
    Prev
    Next
    INDEX
    Explanations

    requests for information or assistance related to issues and questions

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

    Preceding questions or queries

    np_acts-logits-general · gemini-2.0-flash

    asking questions

    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
    SOUNDBITE
    -0.60
    ngrx
    -0.59
    Traits
    -0.41
    schedulers
    -0.41
     tích
    -0.40
    żs
    -0.38
    RegistryLite
    -0.37
    널
    -0.37
    标
    -0.37
    Ndr
    -0.36
    POSITIVE LOGITS
     questions
    1.88
     queries
    1.66
    questions
    1.52
     Questions
    1.45
    Questions
    1.42
     inquiries
    1.39
     Fragen
    1.36
     doubts
    1.33
     Queries
    1.32
     enquiries
    1.28
    Activations Density 0.180%

    No Known Activations