© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    phrases expressing subjective experiences or states of being

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

    "it was" or a similar past tense construction

    np_acts-logits-general · gemini-2.0-flash

    was followed by a description

    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
     itſelf
    -0.76
     Volga
    -0.66
     themſelves
    -0.63
     myſelf
    -0.61
    
    -0.61
    フォーマンス
    -0.60
     raiſ
    -0.60
    хьтан
    -0.59
     whoſe
    -0.59
     bör
    -0.58
    POSITIVE LOGITS
     raining
    0.56
    SourceChecksum
    0.56
     pure
    0.53
     a
    0.52
    COUVER
    0.50
     stressful
    0.50
     بتاريخ
    0.50
     مرئيه
    0.49
     an
    0.49
     قص
    0.49
    Activations Density 0.145%

    No Known Activations