Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14684
    Prev
    Next
    INDEX
    Explanations

    expressions related to morality and ethical beliefs

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

    Follows punctuation within dialogue or reported speech

    np_acts-logits-general · gemini-2.0-flash

    puncutation following agreement

    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
    Personensuche
    -0.83
     propOrder
    -0.83
     myſelf
    -0.76
     itſelf
    -0.72
    VersionUID
    -0.71
    enumii
    -0.71
    onViewCreated
    -0.70
    ientôt
    -0.69
    WriteBarrier
    -0.67
     Eſ
    -0.66
    POSITIVE LOGITS
    確かに
    0.93
    なるほど
    0.91
    Apparently
    0.85
     Apparently
    0.81
    是啊
    0.80
    たしか
    0.79
    这话
    0.79
     Presumably
    0.76
     clearly
    0.73
    Sounds
    0.73
    Activations Density 0.392%

    No Known Activations