© 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. 494
    Prev
    Next
    INDEX
    Explanations

    instances of criticism regarding policy decisions and their implications

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

    Commas after negations or criticisms

    np_acts-logits-general · gemini-2.0-flash

    financial code and data

    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
    Soorten
    -0.57
    initializeApp
    -0.57
    ğun
    -0.56
    generally
    -0.54
     slightly
    -0.54
     generalmente
    -0.53
     pengaruh
    -0.51
    \{\\
    -0.51
     meist
    -0.50
    slightly
    -0.49
    POSITIVE LOGITS
     shame
    0.99
     Shame
    0.97
    shame
    0.94
    Shame
    0.90
     seharusnya
    0.88
     shameful
    0.87
     deberían
    0.83
     Shouldn
    0.82
     Should
    0.79
     disgraceful
    0.79
    Activations Density 0.330%

    No Known Activations