© 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. 10872
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative and regulatory discussions

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

    followed by explanations or arguments

    np_acts-logits-general · gemini-2.0-flash

    issue, concept, or doctrine

    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
    ⓧ
    -0.52
     veille
    -0.47
     Grecs
    -0.46
     déroule
    -0.46
    amerikanischer
    -0.46
    GTCX
    -0.45
     izquier
    -0.45
    addTab
    -0.45
     autorité
    -0.44
     utilisent
    -0.44
    POSITIVE LOGITS
     concept
    1.38
     phenomenon
    1.34
     syndrome
    1.30
     idea
    1.25
     theory
    1.24
     thing
    1.23
     issue
    1.20
     doctrine
    1.13
     trope
    1.13
     notion
    1.12
    Activations Density 0.847%

    No Known Activations