© 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. 11167
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational membership and participation

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

    joining or applying for something

    np_acts-logits-general · gemini-2.0-flash

    joining or applying

    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
    EndContext
    -0.64
     onBind
    -0.55
    AndEndTag
    -0.53
     Мексичка
    -0.51
     ReactDOM
    -0.51
    LookAnd
    -0.50
    enderror
    -0.50
    Архівовано
    -0.50
    المناصب
    -0.50
    stylers
    -0.50
    POSITIVE LOGITS
     join
    0.52
     joined
    0.49
     membership
    0.47
     joining
    0.44
     Join
    0.43
    Membership
    0.41
     enrolled
    0.41
    Join
    0.40
     Joined
    0.39
    加入
    0.39
    Activations Density 0.341%

    No Known Activations