© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10378
    Prev
    Next
    INDEX
    Explanations

    elements related to organization and comparison in lists or sequences

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

    "One" followed by "another"

    np_acts-logits-general · gemini-2.0-flash

    one and another

    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
    <eos>
    -0.40
     Co
    -0.40
      
    -0.40
     Even
    -0.39
    .
    -0.39
     i
    -0.39
     —
    -0.38
    -
    -0.38
    ↵↵
    -0.37
    ?
    -0.37
    POSITIVE LOGITS
     another
    2.64
    another
    2.42
     Another
    2.16
    Another
    2.16
     others
    2.00
     ANOTHER
    1.88
    others
    1.81
     otro
    1.80
     Others
    1.70
    另一
    1.68
    Activations Density 0.290%

    No Known Activations