© 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. 18-GEMMASCOPE-RES-16K
    11. 8290
    Prev
    Next
    INDEX
    Explanations

    phrases that directly address the reader or include personal pronouns

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

    Statements using "you" or "we"

    np_acts-logits-general · gemini-2.0-flash

    you are or had accepts apply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.70
     yourselves
    -0.65
    ędziesz
    -0.52
     frambo
    -0.49
     confirmations
    -0.49
    bda
    -0.49
    ẫn
    -0.47
    gimento
    -0.47
     Celui
    -0.47
    DllImport
    -0.46
    POSITIVE LOGITS
     want
    0.63
    hyrchwyd
    0.62
    انيف
    0.60
     add
    0.59
    parsedMessage
    0.59
    SequentialGroup
    0.58
     typelib
    0.58
     go
    0.58
     ever
    0.57
    paravant
    0.57
    Activations Density 0.102%

    No Known Activations