© 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. 24-GEMMASCOPE-RES-16K
    11. 14319
    Prev
    Next
    INDEX
    Explanations

    elements related to storytelling and performance in a narrative

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

    Future tense auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    will cause delight or amazement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setupUi
    -0.64
    Obituary
    -0.57
    AnchorStyles
    -0.54
    reportWebVitals
    -0.53
     neceff
    -0.53
     juist
    -0.52
    kie
    -0.51
    ArgsConstructor
    -0.50
    TagHelper
    -0.49
    DebuggerNonUser
    -0.49
    POSITIVE LOGITS
     wow
    0.99
     delight
    0.86
    wow
    0.81
     impress
    0.79
     thrill
    0.79
     enth
    0.77
     da
    0.76
     amaze
    0.76
     enchant
    0.74
     tickle
    0.73
    Activations Density 0.154%

    No Known Activations