© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7737
    Prev
    Next
    INDEX
    Explanations

    references to 'cap' or 'capacitance' 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 @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Referències
    -0.81
     imageName
    -0.64
    thodoxy
    -0.64
    levance
    -0.63
     للمعارف
    -0.61
     lama
    -0.61
     מוכ
    -0.61
    PyObject
    -0.61
     Pingback
    -0.60
    ."<
    -0.60
    POSITIVE LOGITS
     cap
    2.72
    Cap
    2.67
     Cap
    2.63
    cap
    2.56
     caps
    2.49
     Caps
    2.34
     CAP
    2.22
    caps
    2.06
    CAP
    2.04
    Caps
    1.98
    Activations Density 0.080%

    No Known Activations