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. 14-GEMMASCOPE-RES-16K
    6. 10751
    Prev
    Next
    INDEX
    Explanations

    concepts related to power and its various forms and implications

    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
     wireType
    -0.71
    fjspx
    -0.69
    GEBURTS
    -0.66
     typelib
    -0.65
     defaultstate
    -0.61
     StringTokenizer
    -0.60
     continuation
    -0.60
     interrupted
    -0.60
     समीक्षाएं
    -0.59
    addCriterion
    -0.59
    POSITIVE LOGITS
     powerful
    1.36
     power
    1.30
    Powerful
    1.29
    powerful
    1.27
     Powerful
    1.24
     powers
    1.13
    power
    1.12
     potent
    1.12
     POWER
    1.10
     puissant
    1.02
    Activations Density 0.337%

    No Known Activations