© 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. 1607
    Prev
    Next
    INDEX
    Explanations

    marker tokens that distinguish sections or segments of text

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

    Text following initial words in sentences

    np_acts-logits-general · gemini-2.0-flash

    web, John, playing, brain, effect, Q, Turkey

    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
     '\\;'
    -1.32
     ―――――
    -1.28
     $_"
    -1.27
     estekak
    -1.24
    )";
    -1.21
    ^(@)
    -1.20
    '):
    -1.20
    "):
    -1.19
    .",
    -1.18
     Мексичка
    -1.18
    POSITIVE LOGITS
    <eos>
    1.67
     
    1.02
    ↵↵
    0.98
    ...
    0.93
    The
    0.93
    ↵
    0.93
    A
    0.86
    I
    0.85
     The
    0.84
      
    0.82
    Activations Density 0.237%

    No Known Activations