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. 4-GEMMASCOPE-RES-16K
    6. 15620
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the personal pronoun "you" and expressions of desire or need

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.71
    ModelAndView
    -0.55
     skor
    -0.54
    例句
    -0.53
    χος
    -0.52
    ABASE
    -0.49
     Lett
    -0.48
    haz
    -0.48
    джет
    -0.47
    항
    -0.45
    POSITIVE LOGITS
     what
    0.85
    AndEndTag
    0.74
    whats
    0.71
     RIPRODUZIONE
    0.70
    what
    0.69
     mijne
    0.69
    What
    0.68
     WHAT
    0.68
     τι
    0.68
     What
    0.67
    Activations Density 0.141%

    No Known Activations