© 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. 1766
    Prev
    Next
    INDEX
    Explanations

    phrases related to apologies and the concept of forgiveness

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

    Expressing contrition or seeking forgiveness

    np_acts-logits-general · gemini-2.0-flash

    apology and retraction

    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
     Мексичка
    -0.56
    esez
    -0.52
     lazy
    -0.51
    Instantiation
    -0.51
    σμο
    -0.50
    ppus
    -0.48
     savez
    -0.45
     StringTokenizer
    -0.45
    ..\..\
    -0.44
    matchCondition
    -0.44
    POSITIVE LOGITS
     apology
    2.11
     apologized
    1.94
     apologizing
    1.90
     apologize
    1.81
     apologies
    1.78
     apologised
    1.72
     apologise
    1.63
     apolog
    1.52
     apologe
    1.47
     forgiven
    1.44
    Activations Density 0.306%

    No Known Activations