© 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. 16-GEMMASCOPE-RES-16K
    11. 12762
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate absence or lack of something

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

    Follows the word "without"

    np_acts-logits-general · gemini-2.0-flash

    without + clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.74
     Monfieur
    -0.73
     Efq
    -0.69
    ſelf
    -0.66
     Jefus
    -0.64
     houſe
    -0.62
     pleaſure
    -0.61
     ejus
    -0.58
     quoque
    -0.55
     purpoſe
    -0.54
    POSITIVE LOGITS
     Without
    1.27
    Without
    1.22
    Ohne
    1.18
     without
    1.18
    without
    1.13
     WITHOUT
    1.08
     ohne
    1.05
    WITHOUT
    1.02
     senza
    0.97
     InputDecoration
    0.96
    Activations Density 0.091%

    No Known Activations