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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 2810
    Prev
    Next
    INDEX
    Explanations

    expressions of intention or plans in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -1.10
     GoogleFonts
    -0.96
     ویکی‌پدیای
    -0.87
     חיצוניים
    -0.84
     NSCoder
    -0.84
    큼
    -0.82
     Roskov
    -0.81
     Cowper
    -0.81
    TypedDataSet
    -0.80
     nakalista
    -0.80
    POSITIVE LOGITS
    Intent
    1.17
    intent
    1.17
     intended
    1.17
     intent
    1.14
     Intent
    1.08
     intends
    1.08
     Intended
    1.03
     Inten
    1.01
    Intended
    1.01
     intend
    0.98
    Activations Density 0.093%

    No Known Activations