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. 21-GEMMASCOPE-RES-16K
    6. 1275
    Prev
    Next
    INDEX
    Explanations

    French phrases related to expressing requirements or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vostro
    -0.89
     Ihnen
    -0.88
    您
    -0.84
     vostri
    -0.84
     vostre
    -0.83
     usted
    -0.83
    Usted
    -0.82
    如果您
    -0.80
     لكم
    -0.79
     vostra
    -0.79
    POSITIVE LOGITS
     thy
    1.48
     thou
    1.40
     thine
    1.16
     thyself
    1.15
    Thou
    1.14
     твое
    1.13
     тво
    1.11
     твои
    1.10
     Thou
    1.09
     Thy
    1.06
    Activations Density 0.201%

    No Known Activations