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. 3350
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantum mechanics and inner product notations

    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
     للمعارف
    -1.03
    /**
    -0.83
    /*
    -0.76
     alimentaire
    -0.76
     stationnement
    -0.75
    Lähteet
    -0.75
    Искәрмәләр
    -0.74
    extré
    -0.74
     Bouch
    -0.74
    acas
    -0.73
    POSITIVE LOGITS
    rangle
    2.52
    langle
    1.75
    〉
    1.18
    ⟩
    1.18
    ⟨
    0.86
    〉
    0.80
    〈
    0.79
     〈
    0.75
    rceil
    0.69
    rfloor
    0.68
    Activations Density 0.104%

    No Known Activations