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. 7-GEMMASCOPE-RES-16K
    6. 4519
    Prev
    Next
    INDEX
    Explanations

    terms related to charging and energy usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -1.01
     doubtnut
    -0.89
    \"");
    -0.89
    >\<
    -0.88
     Romain
    -0.87
     myſelf
    -0.85
     bint
    -0.85
     OBITUARY
    -0.85
    ✨:
    -0.85
     cdti
    -0.84
    POSITIVE LOGITS
     charges
    2.08
     charge
    2.07
    charge
    1.95
     Charge
    1.90
    Charge
    1.87
     Charges
    1.85
    charges
    1.84
     charged
    1.79
     CHARGE
    1.75
    Charges
    1.73
    Activations Density 0.040%

    No Known Activations