© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2166
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing actions or persistent states of being

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

    "Still" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    still + ongoing action/state

    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
     again
    -0.99
    again
    -0.96
     suddenly
    -0.88
    
    -0.85
    ंदीखरीदारी
    -0.85
    Again
    -0.85
     nuevamente
    -0.84
     novamente
    -0.83
    OGND
    -0.82
     Again
    -0.81
    POSITIVE LOGITS
    væ
    0.64
     active
    0.58
     relevant
    0.57
    下去
    0.56
     relevance
    0.54
     after
    0.53
     despite
    0.53
     malgré
    0.52
     nonostante
    0.52
     spite
    0.52
    Activations Density 0.277%

    No Known Activations