© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8825
    Prev
    Next
    INDEX
    Explanations

    concepts related to social responsibility and community improvement

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

    Follows "world" occurring in a positive context

    np_acts-logits-general · gemini-2.0-flash

    ideal world states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    ніципалі
    -0.55
    /**
    -0.45
    spyOn
    -0.45
    Expose
    -0.44
     թվական
    -0.43
    fjspx
    -0.43
     <>",
    -0.43
    transQ
    -0.42
    MENAFN
    -0.41
     itertools
    -0.40
    POSITIVE LOGITS
    ChildScrollView
    0.66
    setVerticalGroup
    0.51
    LookAnd
    0.46
     newOwner
    0.45
    :✨
    0.45
    astify
    0.44
     healthier
    0.43
    اریخ
    0.43
    aktur
    0.42
    delwed
    0.40
    Activations Density 0.189%

    No Known Activations