© 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. 3349
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intention or future actions

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

    Following "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    future intent"gonna" + verb

    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
     كومونز
    -0.83
    ſelves
    -0.82
     ligiloj
    -0.76
    BagConstraints
    -0.76
    Hentet
    -0.70
     الرياضيه
    -0.69
    \{\\
    -0.68
    NonQuery
    -0.68
     pageContext
    -0.68
    最快更新
    -0.67
    POSITIVE LOGITS
     gonna
    0.88
     be
    0.88
     GONNA
    0.81
     Gonna
    0.78
    Gonna
    0.77
     gotta
    0.65
    gonna
    0.63
     lotta
    0.62
     freaking
    0.62
     wanna
    0.62
    Activations Density 0.092%

    No Known Activations