© 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. 8421
    Prev
    Next
    INDEX
    Explanations

    instances of conditional statements and contrasting phrases

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

    Sentences starting with coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    conjunctions introducing divergence

    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
    CloseOperation
    -0.95
    ANSA
    -0.89
    NUMX
    -0.89
     Majefty
    -0.86
     ―――――
    -0.86
    YMMV
    -0.83
    ruik
    -0.83
     auffi
    -0.82
     Monfieur
    -0.82
    ].)
    -0.82
    POSITIVE LOGITS
     it
    0.84
     the
    0.76
     majority
    0.69
      
    0.65
     дан
    0.63
    很多的
    0.63
     nowadays
    0.62
     Nowadays
    0.61
     till
    0.60
     there
    0.60
    Activations Density 0.497%

    No Known Activations