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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8153
    Prev
    Next
    INDEX
    Explanations

    references to specific medical and legal terms and contexts

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

    followed by "is"

    np_acts-logits-general · gemini-2.0-flash

    state or possibility

    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
    ']:
    -0.62
    ()].
    -0.62
    %;">
    -0.61
    RegressionTest
    -0.61
     чтоб
    -0.61
     ];
    -0.60
     ]
    
    -0.60
    ++];
    -0.60
    ()];
    -0.60
    ']}
    -0.60
    POSITIVE LOGITS
     is
    1.81
     has
    1.47
     was
    1.36
     will
    1.25
     can
    1.24
     may
    1.23
     cannot
    1.18
     might
    1.16
     could
    1.11
     isn
    1.09
    Activations Density 4.354%

    No Known Activations