© 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. 4095
    Prev
    Next
    INDEX
    Explanations

    expressions of comparison or specificity, particularly involving the words "this", "that", and related phrases

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

    "this," "that," or "that kind of"

    np_acts-logits-general · gemini-2.0-flash

    this kind of

    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
    værende
    -0.48
    жется
    -0.48
     Du
    -0.47
    发表于
    -0.45
    AddWithValue
    -0.44
     иначе
    -0.42
    kust
    -0.41
    izzano
    -0.40
    wes
    -0.40
     Nes
    -0.39
    POSITIVE LOGITS
     kind
    1.20
     kinds
    0.98
     type
    0.96
     sort
    0.94
     level
    0.90
    kind
    0.89
    kinds
    0.89
     amount
    0.86
     sorts
    0.85
     soort
    0.83
    Activations Density 0.297%

    No Known Activations